<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
     xmlns:dc="http://purl.org/dc/elements/1.1/"
     xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
     xmlns:admin="http://webns.net/mvcb/"
     xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
     xmlns:content="http://purl.org/rss/1.0/modules/content/"
     xmlns:media="http://search.yahoo.com/mrss/">
<channel>
<title>Jat Ai News &amp; Unveiling the Future of Intelligence &amp; : AWS</title>
<link>https://news.jatlink.uk/rss/category/tools-aws</link>
<description>Jat Ai News &amp; Unveiling the Future of Intelligence &amp; : AWS</description>
<dc:language>en</dc:language>
<dc:rights>Copyright 2024 Jat Link Limited &amp; All Rights Reserved.</dc:rights>

<item>
<title>Introducing Claude Haiku 5.5 on AWS</title>
<link>https://news.jatlink.uk/23186</link>
<guid>https://news.jatlink.uk/23186</guid>
<description><![CDATA[ Claude Haiku 5.5 is now available on Amazon Bedrock and Claude Platform on AWS. According to Anthropic, it is the fastest, most efficient model in the Claude 5.5 family, built for subagents and high-volume, cost-sensitive work, and costs around 75% less than Claude Haiku 4.5 for most tasks. This post covers its improvements and how to get started. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/07/ML-22086-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 07 Oct 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Claude, Haiku, 5.5, AWS</media:keywords>
</item>

<item>
<title>Rethinking access control for RAG with Amazon Quick and Amazon Bedrock</title>
<link>https://news.jatlink.uk/23187</link>
<guid>https://news.jatlink.uk/23187</guid>
<description><![CDATA[ Enterprise RAG unlocks insights from knowledge sources like SharePoint, Google Drive, and Confluence, but those sources carry complex permissions. Learn how Amazon Quick and Amazon Bedrock Knowledge Bases enforce document-level access controls in real time, verifying permissions directly with authoritative sources at query time. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/07/ML-22080-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 07 Oct 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Rethinking, access, control, for, RAG, with, Amazon, Quick, and, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Building AI builders: Playbook for closing the AI knowledge&amp;capability gap</title>
<link>https://news.jatlink.uk/23167</link>
<guid>https://news.jatlink.uk/23167</guid>
<description><![CDATA[ The biggest barrier to AI adoption isn&#039;t awareness. It&#039;s the gap between talking about AI and building with it. Here&#039;s the playbook we used to turn non-technical, customer-facing professionals into confident AI builders in six weeks, and how your organization can replicate it. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21448-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 07 Oct 2026 17:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, builders:, Playbook, for, closing, the, knowledge-capability, gap</media:keywords>
</item>

<item>
<title>How Cornerstone OnDemand cut database diagnosis by 78% with Amazon Bedrock</title>
<link>https://news.jatlink.uk/23168</link>
<guid>https://news.jatlink.uk/23168</guid>
<description><![CDATA[ Cornerstone OnDemand built Orion AI, a multi-agent system on Amazon Bedrock and Strands Agents, to turn database operations from reactive firefighting into proactive automation. A three-person team cut database diagnosis from 45 minutes to 10, a 78% reduction, in six months. See the design decisions other teams can reuse. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-20695-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 07 Oct 2026 17:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Cornerstone, OnDemand, cut, database, diagnosis, 78, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Beyond hours saved: Building the business case for agentic automation</title>
<link>https://news.jatlink.uk/23164</link>
<guid>https://news.jatlink.uk/23164</guid>
<description><![CDATA[ The RPA-era ROI model misses most of the value agentic automation creates. This post gives AI center of excellence leaders a framework to size the full value of agents across time savings, exception handling, decision quality, and maintenance economics, and to prioritize which workflows to automate first. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/30/ML-21671-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 07 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Beyond, hours, saved:, Building, the, business, case, for, agentic, automation</media:keywords>
</item>

<item>
<title>How Qlik built grounded, enterprise&amp;scale AI with Amazon Bedrock</title>
<link>https://news.jatlink.uk/23165</link>
<guid>https://news.jatlink.uk/23165</guid>
<description><![CDATA[ Qlik built Qlik Answers on Amazon Bedrock to give its 40,000+ customers grounded, sourced answers across structured and unstructured enterprise data. Learn how a layered, multi-agent architecture with cross-Region inference and Amazon Bedrock Guardrails delivers trusted AI at global scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21310-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 07 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Qlik, built, grounded, enterprise-scale, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Automate remediation post AWS DevOps Agent investigation</title>
<link>https://news.jatlink.uk/23166</link>
<guid>https://news.jatlink.uk/23166</guid>
<description><![CDATA[ AWS DevOps Agent can diagnose production incidents but is kept in observe-and-report mode so it does not change resources directly. This post shows how to use AWS Lambda Durable Functions, Amazon EventBridge, and Amazon Bedrock to turn its investigation summaries into pre-validated fixes an on-call engineer can approve with a single action. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/05/ML-20995-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 07 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, remediation, post, AWS, DevOps, Agent, investigation</media:keywords>
</item>

<item>
<title>Building a context&amp;aware AI assistant on AgentCore and OpenClaw</title>
<link>https://news.jatlink.uk/23106</link>
<guid>https://news.jatlink.uk/23106</guid>
<description><![CDATA[ Off-the-shelf AI assistants forget you between conversations. This post shows how to build a personal assistant that accumulates context using OpenClaw on Amazon Bedrock AgentCore runtime, with AgentCore memory turning disposable chats into durable, structured knowledge you can retrieve with metadata filters. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 06 Oct 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, context-aware, assistant, AgentCore, and, OpenClaw</media:keywords>
</item>

<item>
<title>Responsible AI governance: How AWS positions customers to align with ISO/IEC 42005:2025</title>
<link>https://news.jatlink.uk/23086</link>
<guid>https://news.jatlink.uk/23086</guid>
<description><![CDATA[ AWS invests in tools that help customers align with international standards for responsible AI governance. In this post, we explore the AI system impact assessment: what it is, how it improves enterprise-wide risk management, and how ISO/IEC 42005:2025 codifies best practices for conducting and documenting these assessments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/30/ML-21895-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 06 Oct 2026 17:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Responsible, governance:, How, AWS, positions, customers, align, with, ISOIEC, 42005:2025</media:keywords>
</item>

<item>
<title>Best practices for Amazon SageMaker HyperPod administration and governance</title>
<link>https://news.jatlink.uk/23087</link>
<guid>https://news.jatlink.uk/23087</guid>
<description><![CDATA[ Learn how to administer Amazon SageMaker HyperPod through Amazon SageMaker Unified Studio while preserving cluster governance. This post shows platform teams how to design infrastructure boundaries, govern access, allocate shared capacity, and operate HyperPod consistently across the organization, project, cluster, and workload control layers. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21129-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 06 Oct 2026 17:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Best, practices, for, Amazon, SageMaker, HyperPod, administration, and, governance</media:keywords>
</item>

<item>
<title>Manage Amazon SageMaker HyperPod Spaces directly from SageMaker Studio</title>
<link>https://news.jatlink.uk/23088</link>
<guid>https://news.jatlink.uk/23088</guid>
<description><![CDATA[ Data scientists and ML engineers can now create, configure, start, stop, and open Amazon SageMaker Spaces on SageMaker HyperPod EKS clusters directly from SageMaker Studio. Launch JupyterLab and Code Editor environments in a few clicks, without using command-line tools. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21625-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 06 Oct 2026 17:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Manage, Amazon, SageMaker, HyperPod, Spaces, directly, from, SageMaker, Studio</media:keywords>
</item>

<item>
<title>Build a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova Sonic</title>
<link>https://news.jatlink.uk/23089</link>
<guid>https://news.jatlink.uk/23089</guid>
<description><![CDATA[ Add a voice travel concierge to an airline app with Amazon Bedrock AgentCore, Amazon Nova Sonic for real-time speech, and Amazon Bedrock Knowledge Bases for policy answers. Travelers change seats, check delays, and ask policy questions by voice, while the agent reaches your backend through MCP tools and confirms every change before it writes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21469/Travel-Concierge-App-Demo.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 06 Oct 2026 17:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, voice, travel, concierge, with, Amazon, Bedrock, AgentCore, Managed, Knowledge, Base, and, Nova, Sonic</media:keywords>
</item>

<item>
<title>Introducing GLM 5.3 on Amazon Bedrock</title>
<link>https://news.jatlink.uk/23047</link>
<guid>https://news.jatlink.uk/23047</guid>
<description><![CDATA[ GLM 5.3 from Z.ai is now available on Amazon Bedrock: a 753B-parameter mixture-of-experts model built for coding and long-horizon agentic tasks. Learn how to invoke it with the OpenAI-compatible APIs, cut cost and latency with prompt caching, and run an authorized security test with the open-source Strix agent. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-22047/Strix Demo Video Censored.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 06 Oct 2026 01:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, GLM, 5.3, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Supercharge regulated workloads with Claude Code and Amazon Bedrock</title>
<link>https://news.jatlink.uk/23028</link>
<guid>https://news.jatlink.uk/23028</guid>
<description><![CDATA[ Anthropic Claude Opus 5.5 and Claude Sonnet 5.5 are available on Amazon Bedrock in the AWS GovCloud (US) Regions. Learn how to use them with Claude Code, Anthropic&#039;s agentic coding tool, for compliance-aligned, AI-assisted development on regulated and ITAR workloads. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/23/ML-19466-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 05 Oct 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Supercharge, regulated, workloads, with, Claude, Code, and, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>New agent skill: Amazon SageMaker optimized generative AI inference for your coding agent</title>
<link>https://news.jatlink.uk/23029</link>
<guid>https://news.jatlink.uk/23029</guid>
<description><![CDATA[ Amazon SageMaker optimized generative AI inference introduces the aws-ai-ml skill through the Agent Toolkit for AWS, giving coding agents like Kiro, Claude Code, and Codex deep expertise in inference optimization and benchmarking. Describe what you want, and your agent generates executable SageMaker Python SDK v3 code to benchmark, recommend, and compare deployments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-21968-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 05 Oct 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>New, agent, skill:, Amazon, SageMaker, optimized, generative, inference, for, your, coding, agent</media:keywords>
</item>

<item>
<title>Downgrading user roles in Amazon Quick</title>
<link>https://news.jatlink.uk/23003</link>
<guid>https://news.jatlink.uk/23003</guid>
<description><![CDATA[ Amazon Quick doesn&#039;t offer a direct console path to downgrade a user from Admin or Author to Reader. This post walks through two reliable methods: a manual delete-and-recreate approach and an AWS CLI step-down sequence that downgrades roles safely while preserving asset ownership. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/25/ML-22009-featured-image-1.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 05 Oct 2026 17:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Downgrading, user, roles, Amazon, Quick</media:keywords>
</item>

<item>
<title>Evaluating multi&amp;agent systems for explainability and helpfulness with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/23004</link>
<guid>https://news.jatlink.uk/23004</guid>
<description><![CDATA[ Multi-agent systems need deeper guarantees than fluent responses: they must select the right tools, respect constraints, and explain their decisions. Learn how to build a Strands-based multi-agent supply chain decisioning system and evaluate it with Amazon Bedrock AgentCore Evaluations using built-in, custom, and explainability evaluators. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/01/ML-20163-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 05 Oct 2026 17:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evaluating, multi-agent, systems, for, explainability, and, helpfulness, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Making Amazon Quick enterprise&amp;ready: Automated, auditable cross&amp;account resource promotion</title>
<link>https://news.jatlink.uk/23001</link>
<guid>https://news.jatlink.uk/23001</guid>
<description><![CDATA[ Promoting Amazon Quick resources (agents, action connectors, knowledge bases, flows, and spaces) from a development to a production AWS account has been a manual, error-prone chore. This post shows how to automate cross-account promotion with an idempotent, auditable MCP server on Amazon Bedrock AgentCore. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-21611-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 05 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Making, Amazon, Quick, enterprise-ready:, Automated, auditable, cross-account, resource, promotion</media:keywords>
</item>

<item>
<title>Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases</title>
<link>https://news.jatlink.uk/23002</link>
<guid>https://news.jatlink.uk/23002</guid>
<description><![CDATA[ Build a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions that single-shot retrieval answers poorly. Run the same query through both paths, read the trace events, and compare what each retrieval path costs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-21691-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 05 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agentic, retrieval, with, LangChain, and, Amazon, Bedrock, Knowledge, Bases</media:keywords>
</item>

<item>
<title>Add secure Web Search to Claude Desktop with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/22774</link>
<guid>https://news.jatlink.uk/22774</guid>
<description><![CDATA[ Claude Desktop on Amazon Bedrock is limited to the model&#039;s knowledge cutoff without web search. In this post, we walk through connecting Claude Desktop to Web Search using Amazon Bedrock AgentCore Gateway, with JWT-based inbound authentication through AWS IAM Identity Center and Amazon Cognito. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/30/ML-21694-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 02 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Add, secure, Web, Search, Claude, Desktop, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Fine&amp;tune a search agent with multi&amp;turn RL on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/22775</link>
<guid>https://news.jatlink.uk/22775</guid>
<description><![CDATA[ Fine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost. In this post, we fine-tune an LLM-powered search agent with multi-turn reinforcement learning (MTRL) on Amazon SageMaker AI and share the gains we measured in retrieval quality and reliability. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/01/ML-21889-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 02 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Fine-tune, search, agent, with, multi-turn, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Sweep thousands of leases for compliance using Amazon Quick and the Adjudicated Query pattern</title>
<link>https://news.jatlink.uk/22773</link>
<guid>https://news.jatlink.uk/22773</guid>
<description><![CDATA[ The Adjudicated Query pattern pairs the Amazon Quick chat agent with a bounded MCP server over a deterministic rules engine to deliver provably complete, defensible compliance answers. This post walks through the reference architecture and a deployable AWS CDK sample, using lease compliance as the running example. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/30/ML-21832-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 02 Oct 2026 17:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Sweep, thousands, leases, for, compliance, using, Amazon, Quick, and, the, Adjudicated, Query, pattern</media:keywords>
</item>

<item>
<title>Simplify dashboard drill&amp;down with the Amazon Quick Sight hierarchy filter</title>
<link>https://news.jatlink.uk/22682</link>
<guid>https://news.jatlink.uk/22682</guid>
<description><![CDATA[ Amazon Quick Sight is a fully managed, cloud-native business intelligence (BI) capability for building and publishing interactive dashboards. The new hierarchy filter gives dashboard authors rich, multi-level filtering in a single compact control, reducing clutter and guiding readers to the data they need in fewer steps. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-21595-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 01 Oct 2026 21:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Simplify, dashboard, drill-down, with, the, Amazon, Quick, Sight, hierarchy, filter</media:keywords>
</item>

<item>
<title>Build agent memory with NVIDIA NeMo Agent Toolkit and Amazon S3 Vectors</title>
<link>https://news.jatlink.uk/22678</link>
<guid>https://news.jatlink.uk/22678</guid>
<description><![CDATA[ Learn how to use Amazon S3 Vectors as the persistent memory layer within the NVIDIA NeMo Agent Toolkit (NAT), deployed on Amazon Elastic Kubernetes Service (Amazon EKS). This post shows how NAT&#039;s memory subsystem works and how to implement Amazon S3 Vectors as a custom memory provider, using a multi-agent investment research use case. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/28/ML-21981-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 01 Oct 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, agent, memory, with, NVIDIA, NeMo, Agent, Toolkit, and, Amazon, Vectors</media:keywords>
</item>

<item>
<title>Uplifting conversion across the acquisition funnel with personalization using contextual bandits on AWS</title>
<link>https://news.jatlink.uk/22679</link>
<guid>https://news.jatlink.uk/22679</guid>
<description><![CDATA[ Generative AI makes it cheap to produce personalized content at scale, but which variation do you show each customer? Amazon Payments used a multi-objective contextual bandit on Amazon SageMaker AI to personalize an acquisition funnel, achieving a high single-digit conversion lift for one audience, and learning why content, not the model, was the constraint. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-20979-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 01 Oct 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Uplifting, conversion, across, the, acquisition, funnel, with, personalization, using, contextual, bandits, AWS</media:keywords>
</item>

<item>
<title>Building ambient agents with Amazon Bedrock AgentCore: From event&amp;driven signals to human&amp;in&amp;the&amp;loop workflows</title>
<link>https://news.jatlink.uk/22680</link>
<guid>https://news.jatlink.uk/22680</guid>
<description><![CDATA[ Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on Amazon Bedrock AgentCore using Amazon SQS, AWS Lambda, and Amazon DynamoDB, with a single ask_human tool and a Jobs page for human-in-the-loop review. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/25/ML-19851-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 01 Oct 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, ambient, agents, with, Amazon, Bedrock, AgentCore:, From, event-driven, signals, human-in-the-loop, workflows</media:keywords>
</item>

<item>
<title>Implementing Multi&amp;Environment Access for Claude Platform on AWS</title>
<link>https://news.jatlink.uk/22681</link>
<guid>https://news.jatlink.uk/22681</guid>
<description><![CDATA[ Learn how to configure secure, multi-environment access to Claude Platform on AWS from a single subscription: cross-account SigV4 for AWS workloads, workspace-scoped API keys for developers, and OIDC federation for external environments, with workspace-level isolation in a dedicated AI Services account. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/21/ML-21203-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 01 Oct 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implementing, Multi-Environment, Access, for, Claude, Platform, AWS</media:keywords>
</item>

<item>
<title>Serve live, governed data in AI&amp;built apps with Amazon Quick</title>
<link>https://news.jatlink.uk/22677</link>
<guid>https://news.jatlink.uk/22677</guid>
<description><![CDATA[ With Live Data in Apps in Amazon Quick, AI-built apps query your governed Quick Sight datasets in real time instead of static, build-time snapshots. Each query runs as the person viewing the app, so row-level and column-level security apply per reader. Learn how to build, publish, and share a live-data app using natural language. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/30/ML-22064-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 01 Oct 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Serve, live, governed, data, AI-built, apps, with, Amazon, Quick</media:keywords>
</item>

<item>
<title>How uniopen customized Amazon Nova to their retail moderation policies for production deployment</title>
<link>https://news.jatlink.uk/22661</link>
<guid>https://news.jatlink.uk/22661</guid>
<description><![CDATA[ See how uniopen, a retail platform from Taiwan&#039;s Uni-President Enterprises Group, adapted Amazon Nova 2 Lite to its content-moderation policies using supervised fine-tuning in Amazon SageMaker AI and prompt optimization. Business-relevant evaluation and release gates kept quality in check. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/14/ML-21411-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 01 Oct 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, uniopen, customized, Amazon, Nova, their, retail, moderation, policies, for, production, deployment</media:keywords>
</item>

<item>
<title>Build a multi&amp;agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances</title>
<link>https://news.jatlink.uk/22558</link>
<guid>https://news.jatlink.uk/22558</guid>
<description><![CDATA[ Amazon Bedrock AgentCore Runtime Instances gives multi-agent workflows AWS managed EC2 infrastructure with GPUs, persistent volumes, and multi-day sessions. In this post, we deploy a three-agent music production pipeline where the agents colocate on one GPU instance, share a filesystem, and hand work to each other to produce a finished track. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/28/ML-21762-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 30 Sep 2026 17:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, multi-agent, music, production, pipeline, Amazon, Bedrock, AgentCore, Runtime, Instances</media:keywords>
</item>

<item>
<title>Query claims in natural language with Amazon Bedrock Knowledge Bases</title>
<link>https://news.jatlink.uk/22557</link>
<guid>https://news.jatlink.uk/22557</guid>
<description><![CDATA[ This technical how-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions with citations. It covers ingesting claim documents from Amazon S3, querying with the AgenticRetrieveStream API, multi-turn follow-ups, metadata filters, and contextual grounding guardrails. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/28/ML-21629-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 30 Sep 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Query, claims, natural, language, with, Amazon, Bedrock, Knowledge, Bases</media:keywords>
</item>

<item>
<title>Amazon Bedrock expands Claude model availability to in&amp;country inferencing in India</title>
<link>https://news.jatlink.uk/22516</link>
<guid>https://news.jatlink.uk/22516</guid>
<description><![CDATA[ Anthropic&#039;s Claude Opus 5, Claude Sonnet 5, and Claude Haiku 4.5 are now available in India through Amazon Bedrock geographic cross-Region inference. You can access these models while processing data within the India Regions, and get started from the Amazon Bedrock console or with the Messages, InvokeModel, and Converse APIs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-21953-featured-image-1.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 30 Sep 2026 05:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Bedrock, expands, Claude, model, availability, in-country, inferencing, India</media:keywords>
</item>

<item>
<title>Introducing Anthropic models on Amazon Bedrock for in&amp;region inference in Seoul and Singapore</title>
<link>https://news.jatlink.uk/22517</link>
<guid>https://news.jatlink.uk/22517</guid>
<description><![CDATA[ Amazon Bedrock now supports Anthropic&#039;s Claude Opus 5 and Claude Sonnet 5 with in-region inference in Seoul, and Claude Sonnet 5 in Singapore. If you have local data processing requirements in South Korea or Singapore, you can now use these Anthropic models at scale, with inference processed entirely within the Region you call. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-22088-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 30 Sep 2026 05:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Anthropic, models, Amazon, Bedrock, for, in-region, inference, Seoul, and, Singapore</media:keywords>
</item>

<item>
<title>Prompt engineering by Quick component: Patterns and pitfalls</title>
<link>https://news.jatlink.uk/22489</link>
<guid>https://news.jatlink.uk/22489</guid>
<description><![CDATA[ Part 2 of our Amazon Quick prompt engineering series goes component by component. Learn the prompt patterns that get the best results from Amazon Quick Research, Quick Flows, Quick Sight, chat agents, and action integrations, plus the common pitfalls to avoid. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/24/ML-20527-part2-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 29 Sep 2026 21:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Prompt, engineering, Quick, component:, Patterns, and, pitfalls</media:keywords>
</item>

<item>
<title>Building an AI&amp;powered contract intelligence platform with Amazon Quick and Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/22490</link>
<guid>https://news.jatlink.uk/22490</guid>
<description><![CDATA[ Manually extracting data from hundreds of vendor contracts doesn&#039;t scale, and RAG chat tools fall short on portfolio-wide questions. This post shares a contract intelligence platform on AWS that uses AI agents to extract and verify contract fields, then answers aggregate and single-contract questions through Amazon Quick analytics. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/23/ML-21546-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 29 Sep 2026 21:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, AI-powered, contract, intelligence, platform, with, Amazon, Quick, and, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Bring near&amp;Astra intelligence to everyday work with GPT&amp;6.1 Sol on Amazon Bedrock</title>
<link>https://news.jatlink.uk/22487</link>
<guid>https://news.jatlink.uk/22487</guid>
<description><![CDATA[ GPT-6.1 Sol is now generally available on Amazon Bedrock, bringing stronger reasoning to coding, computer use, and professional workloads that run frequently. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/29/ML-22090-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 29 Sep 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Bring, near-Astra, intelligence, everyday, work, with, GPT-6.1, Sol, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Prompt engineering fundamentals for Amazon Quick</title>
<link>https://news.jatlink.uk/22488</link>
<guid>https://news.jatlink.uk/22488</guid>
<description><![CDATA[ Prompt engineering in Amazon Quick shapes how accurately its AI-powered features respond to your requests. Part 1 of a two-part series covers the foundational principles and reusable frameworks (specificity, context-setting, few-shot examples, and the CRISPE framework) for consistent, high-quality results across Amazon Quick. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/24/ML-20527-part1-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 29 Sep 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Prompt, engineering, fundamentals, for, Amazon, Quick</media:keywords>
</item>

<item>
<title>How Condé Nast built multimodal video discovery with Amazon Bedrock</title>
<link>https://news.jatlink.uk/22460</link>
<guid>https://news.jatlink.uk/22460</guid>
<description><![CDATA[ Condé Nast&#039;s editorial teams spent an average of 250 minutes per task searching a library of more than 140,000 videos using only titles and descriptions. Working with the AWS Generative AI Innovation Center, they built a multimodal video discovery solution on Amazon Bedrock and Amazon OpenSearch Service that cut discovery time to under 2 minutes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/18/ML-21598-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 29 Sep 2026 17:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Condé, Nast, built, multimodal, video, discovery, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Grok 4.7 is now available on Amazon Bedrock</title>
<link>https://news.jatlink.uk/22409</link>
<guid>https://news.jatlink.uk/22409</guid>
<description><![CDATA[ xAI&#039;s Grok 4.7 is now available on Amazon Bedrock: a frontier model for coding, long-running agents, and knowledge work. It offers a 500K token context window and four configurable reasoning effort levels, reachable through the Responses, Chat Completions, and Converse APIs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/28/ML-21934-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 29 Sep 2026 01:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Grok, 4.7, now, available, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Generate images and video with vLLM&amp;Omni on SageMaker AI – Part 2</title>
<link>https://news.jatlink.uk/22390</link>
<guid>https://news.jatlink.uk/22390</guid>
<description><![CDATA[ Deploy two generative media models from one AWS vLLM-Omni Deep Learning Container on Amazon SageMaker AI. Generate an image with FLUX.2-klein through real-time inference, then animate it into video with Wan2.1-VACE through asynchronous inference, and retrieve the MP4 from Amazon S3. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21866/figure-3-streamlit-ui-demo.mp4" length="49398" type="image/jpeg"/>
<pubDate>Mon, 28 Sep 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Generate, images, and, video, with, vLLM-Omni, SageMaker, –, Part</media:keywords>
</item>

<item>
<title>Build real&amp;time voice applications with vLLM&amp;Omni on SageMaker AI – Part 1</title>
<link>https://news.jatlink.uk/22389</link>
<guid>https://news.jatlink.uk/22389</guid>
<description><![CDATA[ Deploy a text-to-speech model on Amazon SageMaker AI with the AWS vLLM-Omni Deep Learning Container and stream generated speech over a persistent bidirectional connection. This Part 1 tutorial deploys Qwen3-TTS and streams speech through a Gradio application. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/23/ML-21837-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 28 Sep 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, real-time, voice, applications, with, vLLM-Omni, SageMaker, –, Part</media:keywords>
</item>

<item>
<title>Introducing Claude Sonnet 5.5 on AWS</title>
<link>https://news.jatlink.uk/22388</link>
<guid>https://news.jatlink.uk/22388</guid>
<description><![CDATA[ Claude Sonnet 5.5 is now available on Amazon Bedrock and Claude Platform on AWS. It&#039;s a smarter, more efficient Sonnet model for focused coding and knowledge work, with a lower cost per task at faster speed. This post covers what&#039;s new, when to choose Sonnet, and how to get started. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/28/ML-22023-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 28 Sep 2026 21:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Claude, Sonnet, 5.5, AWS</media:keywords>
</item>

<item>
<title>Implementing synthetic monitoring using Amazon Nova Act</title>
<link>https://news.jatlink.uk/22366</link>
<guid>https://news.jatlink.uk/22366</guid>
<description><![CDATA[ Learn an agent-driven approach to synthetic monitoring using Amazon Nova Act and Amazon Bedrock AgentCore. The post covers the architecture and patterns for resilient, managed user-journey validation that moves beyond brittle UI scripts, with a complete sample implementation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-20230-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 28 Sep 2026 17:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implementing, synthetic, monitoring, using, Amazon, Nova, Act</media:keywords>
</item>

<item>
<title>Automating Amazon Textract adapter lifecycle management across accounts</title>
<link>https://news.jatlink.uk/22367</link>
<guid>https://news.jatlink.uk/22367</guid>
<description><![CDATA[ Learn how to operationalize Amazon Textract Custom Queries adapters for production: infrastructure as code with AWS CloudFormation and Terraform, a cross-account adapter promotion process, a pre-classification routing pattern for multiple form versions, and production security controls such as VPC endpoints, encryption, and least-privilege IAM. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/23/ML-21054-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 28 Sep 2026 17:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automating, Amazon, Textract, adapter, lifecycle, management, across, accounts</media:keywords>
</item>

<item>
<title>Deploying real&amp;time personalized speech with Qwen3&amp;TTS on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/22177</link>
<guid>https://news.jatlink.uk/22177</guid>
<description><![CDATA[ Deploy the publicly available Qwen3-TTS-12Hz-1.7B-Base text-to-speech model from Amazon SageMaker JumpStart to a fully managed, real-time endpoint, and clone a voice from a short reference clip. Cross-lingual cloning preserves the speaker&#039;s identity across languages. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20646/reference_original_input.wav" length="49398" type="image/jpeg"/>
<pubDate>Fri, 25 Sep 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploying, real-time, personalized, speech, with, Qwen3-TTS, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput</title>
<link>https://news.jatlink.uk/22174</link>
<guid>https://news.jatlink.uk/22174</guid>
<description><![CDATA[ Learn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Amazon S3 and increased aggregate reinforcement learning rollout throughput by 40% for large-scale RLHF and GRPO training. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/24/ML-21346-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 25 Sep 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scaling, MoE, reinforcement, learning, Amazon, EKS, with, EFA, and, DeepEP, with, 40, more, throughput</media:keywords>
</item>

<item>
<title>Accelerate multimodal RL training with SkyRL on Amazon SageMaker HyperPod</title>
<link>https://news.jatlink.uk/22175</link>
<guid>https://news.jatlink.uk/22175</guid>
<description><![CDATA[ Learn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the container image, launching a Ray cluster from SageMaker Studio, submitting and monitoring the job, and hosting the trained LoRA adapter for inference. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/23/ML-21828-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 25 Sep 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerate, multimodal, training, with, SkyRL, Amazon, SageMaker, HyperPod</media:keywords>
</item>

<item>
<title>NarrateAI: production&amp;ready LLM quality assurance on Amazon Bedrock</title>
<link>https://news.jatlink.uk/22176</link>
<guid>https://news.jatlink.uk/22176</guid>
<description><![CDATA[ NarrateAI delivers production-ready LLM quality assurance on Amazon Bedrock. This post details five techniques—adaptive pipeline orchestration, cross-account multi-model failover, real-time streaming evaluation, composite evaluation, and data accuracy verification—that reach about 99% numerical accuracy while streaming responses in real time. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/22/ML-20546-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 25 Sep 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>NarrateAI:, production-ready, LLM, quality, assurance, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How Datacor built self&amp;service rental analytics with Amazon Quick Sight</title>
<link>https://news.jatlink.uk/22151</link>
<guid>https://news.jatlink.uk/22151</guid>
<description><![CDATA[ Learn how Datacor built a self-service rental analytics experience for gas and welding distributors by embedding Amazon Quick Sight dashboards and natural language querying into its TrackAbout platform, powered by an automated cross-cloud data pipeline and multi-tenant row-level security. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/17/ML-20632-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 25 Sep 2026 17:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Datacor, built, self-service, rental, analytics, with, Amazon, Quick, Sight</media:keywords>
</item>

<item>
<title>Multi&amp;Region training with Amazon SageMaker HyperPod and Qumulo</title>
<link>https://news.jatlink.uk/22152</link>
<guid>https://news.jatlink.uk/22152</guid>
<description><![CDATA[ Amazon SageMaker HyperPod and Cloud Native Qumulo let you place training compute in one AWS Region while keeping your dataset in another. This post shares the architecture and validation results from a cross-Region training run, where a remote cluster matched a co-located cluster&#039;s throughput after a brief NeuralCache warmup. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/17/ML-19515-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 25 Sep 2026 17:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Multi-Region, training, with, Amazon, SageMaker, HyperPod, and, Qumulo</media:keywords>
</item>

<item>
<title>Aderant builds intelligent ticket triage with Amazon Nova</title>
<link>https://news.jatlink.uk/22094</link>
<guid>https://news.jatlink.uk/22094</guid>
<description><![CDATA[ Learn how Aderant built an intelligent ticket triage system on Amazon Nova Lite through Amazon Bedrock, automating context gathering, classification, routing, and knowledge enrichment for its cloud operations team. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/21/ML-21388-featured-image-1.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 24 Sep 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Aderant, builds, intelligent, ticket, triage, with, Amazon, Nova</media:keywords>
</item>

<item>
<title>Speaker&amp;labeled transcription with WhisperX on SageMaker AI</title>
<link>https://news.jatlink.uk/22092</link>
<guid>https://news.jatlink.uk/22092</guid>
<description><![CDATA[ The AWS WhisperX Deep Learning Container packages Whisper, wav2vec2 forced alignment, and speaker diarization into a GPU-ready image. Learn how to deploy it to Amazon SageMaker AI real-time and asynchronous endpoints for word-level, speaker-labeled transcription, plus the production details that matter: the GPU AMI pin, scaling, and cost controls. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21846/realtime_endpoint_whisperx-flight1549-demo.mp3" length="49398" type="image/jpeg"/>
<pubDate>Thu, 24 Sep 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Speaker-labeled, transcription, with, WhisperX, SageMaker</media:keywords>
</item>

<item>
<title>Build a multi&amp;account AI agent with AgentCore Gateway and MCP</title>
<link>https://news.jatlink.uk/22093</link>
<guid>https://news.jatlink.uk/22093</guid>
<description><![CDATA[ Build a multi-account architecture that keeps each team&#039;s data in its own AWS account while giving AI agents a unified way to query across them. A central platform account runs the agent using Amazon Bedrock AgentCore Gateway and MCP, while line-of-business accounts expose their data as MCP servers with secure cross-account access and fine-grained authorization. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/21/ML-20091-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 24 Sep 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, multi-account, agent, with, AgentCore, Gateway, and, MCP</media:keywords>
</item>

<item>
<title>Use open weight models as your AI coding agent with Amazon Bedrock</title>
<link>https://news.jatlink.uk/22030</link>
<guid>https://news.jatlink.uk/22030</guid>
<description><![CDATA[ Pair OpenCode, an open-source terminal-native AI coding agent, with open weight models on Amazon Bedrock to get a secure, flexible, pay-per-use coding assistant. Learn how to configure multi-model workflows, match the right model to each task, and keep your data in your own AWS account with no infrastructure to manage. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/22/ML-21055-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 23 Sep 2026 23:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Use, open, weight, models, your, coding, agent, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>From portal&amp;hopping to instant answers: HEMA’s journey with MCP and Amazon Bedrock</title>
<link>https://news.jatlink.uk/22028</link>
<guid>https://news.jatlink.uk/22028</guid>
<description><![CDATA[ HEMA, a 100-year-old Dutch retailer, turned developer portal-hopping into instant answers by building HAL, an internal AI assistant on Amazon Bedrock AgentCore. Using Model Context Protocol (MCP), HAL delivers governed knowledge inside the tools teams already use, with no AWS credentials on the client and security anchored in Microsoft Entra ID. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/21/ML-21352-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 23 Sep 2026 23:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, portal-hopping, instant, answers:, HEMA’s, journey, with, MCP, and, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Agentic conversational video intelligence built on AWS</title>
<link>https://news.jatlink.uk/22029</link>
<guid>https://news.jatlink.uk/22029</guid>
<description><![CDATA[ Learn how to build a conversational video intelligence solution on AWS using an agentic architecture. A single Strands Agents SDK agent orchestrates Amazon Bedrock, Amazon Rekognition, and Amazon Transcribe at runtime, deciding which service to call so you can ask natural language questions about your videos and get answers in seconds. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/17/ML-21279-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 23 Sep 2026 23:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agentic, conversational, video, intelligence, built, AWS</media:keywords>
</item>

<item>
<title>Claude Opus 5.5 is now available on AWS</title>
<link>https://news.jatlink.uk/21930</link>
<guid>https://news.jatlink.uk/21930</guid>
<description><![CDATA[ Claude Opus 5.5, Anthropic&#039;s most capable Opus model for agentic coding, knowledge work, and long-running tasks, is now available on Amazon Bedrock and Claude Platform on AWS. This post covers what&#039;s new in Opus 5.5, practical guidance, and how to start building with the model on Amazon Bedrock. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/22/ML-22003-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 22:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Claude, Opus, 5.5, now, available, AWS</media:keywords>
</item>

<item>
<title>Evaluate skill&amp;equipped agents with Strands Evals and Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21931</link>
<guid>https://news.jatlink.uk/21931</guid>
<description><![CDATA[ Skills let you encode domain-specific procedures as reusable, portable instructions for agents, but a fluent answer doesn&#039;t prove the agent picked the right skill or followed it. Learn how to measure skill selection and instruction following with Strands Evals and Amazon Bedrock AgentCore Evaluations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/16/ML-21794-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 22:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evaluate, skill-equipped, agents, with, Strands, Evals, and, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Bring more intelligence to everyday work with GPT&amp;6 Sol and GPT&amp;6 Luna on Amazon Bedrock</title>
<link>https://news.jatlink.uk/21929</link>
<guid>https://news.jatlink.uk/21929</guid>
<description><![CDATA[ GPT-6 Sol and GPT-6 Luna are now generally available on Amazon Bedrock, giving you more options to match intelligence and efficiency to each workload. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/21/ML-21956-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Bring, more, intelligence, everyday, work, with, GPT-6, Sol, and, GPT-6, Luna, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How Tata Elxsi detects industrial safety risks in seconds on AWS</title>
<link>https://news.jatlink.uk/21909</link>
<guid>https://news.jatlink.uk/21909</guid>
<description><![CDATA[ Learn how Tata Elxsi built IRIS, a real-time industrial safety platform on AWS. IRIS filters camera video at the edge, streams metadata through Amazon Kinesis, runs computer vision on Amazon SageMaker AI, and correlates detections into high-confidence alerts, detecting unsafe conditions in seconds instead of minutes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/18/ML-19998-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Tata, Elxsi, detects, industrial, safety, risks, seconds, AWS</media:keywords>
</item>

<item>
<title>Extending public sector intelligence with Agentforce and AWS</title>
<link>https://news.jatlink.uk/21910</link>
<guid>https://news.jatlink.uk/21910</guid>
<description><![CDATA[ Public sector agencies process large volumes of unstructured evidence, such as body camera footage and scanned documents. This post shows how to combine Amazon Bedrock Data Automation with the Model Context Protocol (MCP) to turn that data into structured insights and surface them through natural language queries in Salesforce Agentforce. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/11/ML-20933-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Extending, public, sector, intelligence, with, Agentforce, and, AWS</media:keywords>
</item>

<item>
<title>How Reactiv automates mobile commerce 80% faster with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21906</link>
<guid>https://news.jatlink.uk/21906</guid>
<description><![CDATA[ Reactiv used Amazon Bedrock AgentCore to build a multi-agent AI Scheduler that autonomously refreshes Shopify merchants&#039; mobile apps on a schedule, reducing merchant configuration time by 80% and getting to production 33% faster. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/18/ML-21280-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 18:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Reactiv, automates, mobile, commerce, 80, faster, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Right&amp;size generative AI endpoints with concurrency sweeps on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/21907</link>
<guid>https://news.jatlink.uk/21907</guid>
<description><![CDATA[ Concurrency sweeps help you right-size a generative AI endpoint on Amazon SageMaker AI by systematically benchmarking it at increasing load levels. This post walks through deploying a model, running automated concurrency sweeps with the CreateAIBenchmarkJob API, and using the results to make data-driven capacity decisions about fleet size. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/17/ML-21905-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 18:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Right-size, generative, endpoints, with, concurrency, sweeps, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>How Trane gets building insights 60x faster with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21908</link>
<guid>https://news.jatlink.uk/21908</guid>
<description><![CDATA[ In about four weeks, Trane Technologies built an AI-powered agentic solution on Amazon Bedrock AgentCore that reduced a 20-minute, multi-screen building diagnostic workflow to a 20-second natural language interaction, a 60x improvement in time-to-insight. This post shares the architectural approach and key design decisions behind the solution. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/16/ML-21136-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 22 Sep 2026 18:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Trane, gets, building, insights, 60x, faster, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>xAI’s Grok 4.6 is now available in Amazon Bedrock</title>
<link>https://news.jatlink.uk/21841</link>
<guid>https://news.jatlink.uk/21841</guid>
<description><![CDATA[ xAI&#039;s Grok 4.6 is now available in Amazon Bedrock: a frontier model for long-running agents, coding, and knowledge work, with a 500K token context window and four reasoning effort levels. It runs on both the bedrock-mantle and bedrock-runtime endpoints, with Converse API and cross-Region inference support. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/17/ML-21784-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 21 Sep 2026 22:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>xAI’s, Grok, 4.6, now, available, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How Benchling secured multi&amp;tenant AI agents with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21817</link>
<guid>https://news.jatlink.uk/21817</guid>
<description><![CDATA[ Learn how Benchling built a defense-in-depth security architecture to run untrusted, AI agent-generated scientific code across thousands of life sciences tenants using Amazon Bedrock AgentCore Code Interpreter in VPC mode, combined with Amazon Route 53 Resolver DNS Firewall and VPC endpoint policies to block data exfiltration, including through DNS. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/26/ML-21025-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 21 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Benchling, secured, multi-tenant, agents, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Reducing medical claims review time with AI on AWS: The EXL Medical IDP solution</title>
<link>https://news.jatlink.uk/21818</link>
<guid>https://news.jatlink.uk/21818</guid>
<description><![CDATA[ EXL built an AI-powered Medical intelligent document processing (IDP) solution on AWS, combining IDP with domain-specific large language models on Amazon SageMaker and Amazon Bedrock to extract, summarize, and query medical records at enterprise scale and cut claims review time from over 100 minutes per case. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/15/ML-21250-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 21 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reducing, medical, claims, review, time, with, AWS:, The, EXL, Medical, IDP, solution</media:keywords>
</item>

<item>
<title>How BMW Group detects cost anomalies across 14,000 cloud accounts</title>
<link>https://news.jatlink.uk/21815</link>
<guid>https://news.jatlink.uk/21815</guid>
<description><![CDATA[ BMW Group operates CLEA, a FinOps platform monitoring more than 14,000 cloud accounts. This post shows how BMW added automated daily cost anomaly detection, moving from reactive dashboards to proactive alerts using Prophet forecasting, AWS Step Functions, and a serverless pipeline that processes every account for about $50 per month. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/16/ML-21627-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 21 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, BMW, Group, detects, cost, anomalies, across, 14, 000, cloud, accounts</media:keywords>
</item>

<item>
<title>Run Positron on Amazon SageMaker AI for data science workflows</title>
<link>https://news.jatlink.uk/21816</link>
<guid>https://news.jatlink.uk/21816</guid>
<description><![CDATA[ Positron, Posit&#039;s IDE for data science, now runs on Amazon SageMaker AI. This post shows how a data scientist explores an Amazon Athena table, validates features in R, trains an XGBoost model in Python, deploys a real-time SageMaker AI endpoint, and reports results with Quarto, all in one governed SageMaker Studio Space. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/18/ML-21876-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 21 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Run, Positron, Amazon, SageMaker, for, data, science, workflows</media:keywords>
</item>

<item>
<title>Amazon SageMaker Inference: 2026 year&amp;to&amp;date launches in review</title>
<link>https://news.jatlink.uk/21636</link>
<guid>https://news.jatlink.uk/21636</guid>
<description><![CDATA[ Amazon SageMaker AI shipped 13 inference launches in the first half of 2026 across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference. This post reviews each launch, from inference recommendations and capacity-aware instance pools to tiered KV caching and disaggregated prefill and decode. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/18/ML-21809-featured-image-1.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 18 Sep 2026 22:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, SageMaker, Inference:, 2026, year-to-date, launches, review</media:keywords>
</item>

<item>
<title>Introducing Amazon SageMaker HyperPod Inference Gateway</title>
<link>https://news.jatlink.uk/21620</link>
<guid>https://news.jatlink.uk/21620</guid>
<description><![CDATA[ Amazon SageMaker HyperPod Inference Gateway is a Kubernetes-native, GPU-aware routing add-on for Amazon EKS. It uses real-time GPU signals to send each inference request to the best-suited pod, cutting first-token latency by up to 82% with no changes to your model servers or client applications. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/16/ML-21822-featured-image-2.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 18 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Amazon, SageMaker, HyperPod, Inference, Gateway</media:keywords>
</item>

<item>
<title>Introducing Kimi K3 on Amazon Bedrock</title>
<link>https://news.jatlink.uk/21616</link>
<guid>https://news.jatlink.uk/21616</guid>
<description><![CDATA[ Kimi K3 from Moonshot AI is now available on Amazon Bedrock, giving you a powerful new open-weight option for coding and knowledge work. It offers native vision, a 1-million-token context window, and explicit prompt caching to reduce latency and input costs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21636/OpenCode K3 Demo.mp4" length="49398" type="image/jpeg"/>
<pubDate>Fri, 18 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Kimi, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Deploy Hugging Face models on Amazon SageMaker AI with coding agents</title>
<link>https://news.jatlink.uk/21619</link>
<guid>https://news.jatlink.uk/21619</guid>
<description><![CDATA[ Deploy production-ready Hugging Face models on Amazon SageMaker AI using six open-source agent skills. Point a coding agent at a model and get back a real-time endpoint with the right serving container, autoscaling, Amazon CloudWatch alarms, and a verified teardown path. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/15/ML-21283-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 18 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploy, Hugging, Face, models, Amazon, SageMaker, with, coding, agents</media:keywords>
</item>

<item>
<title>Migrating multi&amp;model AI agents to Amazon Bedrock AgentCore runtime</title>
<link>https://news.jatlink.uk/21617</link>
<guid>https://news.jatlink.uk/21617</guid>
<description><![CDATA[ Migrate a multi-model healthcare AI agent from self-managed Amazon ECS with AWS Fargate to Amazon Bedrock AgentCore runtime, preserving triple-model orchestration and vector-enhanced knowledge retrieval while reducing infrastructure management. The framework-agnostic pattern applies across healthcare, financial services, and manufacturing. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/ML-21510-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 18 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Migrating, multi-model, agents, Amazon, Bedrock, AgentCore, runtime</media:keywords>
</item>

<item>
<title>The new AgentCore runtime: Elastic, optimized, and consistently fast starts</title>
<link>https://news.jatlink.uk/21618</link>
<guid>https://news.jatlink.uk/21618</guid>
<description><![CDATA[ Today we are announcing the new AgentCore runtime, a capability of Amazon Bedrock AgentCore built for the speed, flexibility, and cost efficiency that production agents demand. It reclaims memory as sessions release it and delivers consistent cold starts regardless of image size or concurrency. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/17/ML-21766-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 18 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>The, new, AgentCore, runtime:, Elastic, optimized, and, consistently, fast, starts</media:keywords>
</item>

<item>
<title>Reduce time&amp;to&amp;hire for quality candidates with AI&amp;powered Amazon Connect Talent</title>
<link>https://news.jatlink.uk/21544</link>
<guid>https://news.jatlink.uk/21544</guid>
<description><![CDATA[ Amazon Connect Talent is an AI hiring solution built for talent acquisition leaders managing scaled hiring. It delivers AI-led interviews, data-driven assessments, and consistent evaluation, helping recruiters identify strong candidates more efficiently while providing applicants with a flexible interview experience. Informed by decades of Amazon&#039;s hiring science, Amazon Connect Talent provides transparency for every assessment, interview, and candidate score, enabling recruiters to stay in control of final hiring decisions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/16/Reduce-time-to-hire-for-quality-candidates-with-AI-powered-Amazon-Connect-Talent.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 17 Sep 2026 22:00:04 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reduce, time-to-hire, for, quality, candidates, with, AI-powered, Amazon, Connect, Talent</media:keywords>
</item>

<item>
<title>How MRH Trowe enabled secure self&amp;service AI agents in financial services</title>
<link>https://news.jatlink.uk/21523</link>
<guid>https://news.jatlink.uk/21523</guid>
<description><![CDATA[ Learn how MRH Trowe, one of Germany&#039;s leading commercial and industrial insurance brokers, gave about 400 employees secure, self-service access to AI agents in its first month of production - using Strands Agents, Amazon Bedrock AgentCore, and LibreChat to meet the security, data residency, and compliance requirements of the German financial sector. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/15/ML-21177-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 17 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, MRH, Trowe, enabled, secure, self-service, agents, financial, services</media:keywords>
</item>

<item>
<title>Implementing defense&amp;in&amp;depth authorization for MCP tools on Amazon Quick</title>
<link>https://news.jatlink.uk/21524</link>
<guid>https://news.jatlink.uk/21524</guid>
<description><![CDATA[ Learn how to enforce defense-in-depth authorization for Model Context Protocol (MCP) tools on Amazon Quick. This walkthrough wires Microsoft Entra ID group and claims-based JWTs through an Amazon Bedrock AgentCore Gateway interceptor to apply per-user, per-tool role-based and attribute-based access control, with a server-side check and an immutable audit trail. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/15/ML-21168-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 17 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implementing, defense-in-depth, authorization, for, MCP, tools, Amazon, Quick</media:keywords>
</item>

<item>
<title>Enhancing industrial safety AI with synthetic data on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/21525</link>
<guid>https://news.jatlink.uk/21525</guid>
<description><![CDATA[ Learn how to build a synthetic data augmentation pipeline on Amazon SageMaker AI and Amazon Rekognition that generates photo-realistic, auto-labeled training images for industrial safety AI. This approach improved person detection by up to 160% without manual annotation or hazardous data collection near heavy machinery. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/01/ML-20809-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 17 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Enhancing, industrial, safety, with, synthetic, data, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>A serverless, data&amp;driven Git metrics dashboard using Amazon Quick Sight</title>
<link>https://news.jatlink.uk/21521</link>
<guid>https://news.jatlink.uk/21521</guid>
<description><![CDATA[ Learn how to build a fully serverless pipeline that automatically collects Git metrics from GitHub and GitLab and visualizes them in interactive Amazon Quick Sight dashboards, giving engineering teams near-real-time delivery analytics at low cost. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/11/ML-21183-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 17 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>serverless, data-driven, Git, metrics, dashboard, using, Amazon, Quick, Sight</media:keywords>
</item>

<item>
<title>Selecting a vector store for Amazon Bedrock Knowledge Bases</title>
<link>https://news.jatlink.uk/21520</link>
<guid>https://news.jatlink.uk/21520</guid>
<description><![CDATA[ Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors across three RAG use cases, with benchmarks and a practical selection framework. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/09/ML-19758-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 17 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Selecting, vector, store, for, Amazon, Bedrock, Knowledge, Bases</media:keywords>
</item>

<item>
<title>A shared agentic platform for Wood Mackenzie, on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21522</link>
<guid>https://news.jatlink.uk/21522</guid>
<description><![CDATA[ Wood Mackenzie built APEX, a shared agentic AI platform on Amazon Bedrock AgentCore so every team can ship production agents without rebuilding runtime, identity, observability, and guardrails from scratch. Learn why they chose AgentCore, how APEX Studio operates it, and where multi-agent systems go next. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/16/ML-21057-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 17 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>shared, agentic, platform, for, Wood, Mackenzie, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Improving HCLS AI reasoning with open&amp;source agent skills</title>
<link>https://news.jatlink.uk/21450</link>
<guid>https://news.jatlink.uk/21450</guid>
<description><![CDATA[ AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills across 11 HCLS domains that close this gap, with installation steps, three worked use cases, and a 410-prompt evaluation showing a 70-86% win rate. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21213/quick-desktop-risk-adjustment-withskill.mp4" length="49398" type="image/jpeg"/>
<pubDate>Wed, 16 Sep 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Improving, HCLS, reasoning, with, open-source, agent, skills</media:keywords>
</item>

<item>
<title>Fault tolerant distributed training on Amazon EKS using NVRx</title>
<link>https://news.jatlink.uk/21451</link>
<guid>https://news.jatlink.uk/21451</guid>
<description><![CDATA[ Integrate NVIDIA Resiliency Extension (NVRx) into PyTorch FSDP training on Amazon EKS to overlap checkpoint I/O with training and recover from GPU faults in seconds. This post covers async checkpointing, in-process restart, and ft_launcher in-job restart, with H100 benchmarks at 2 to 8 nodes showing 99%+ training efficiency and second-scale recovery. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/ML-20900-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 16 Sep 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Fault, tolerant, distributed, training, Amazon, EKS, using, NVRx</media:keywords>
</item>

<item>
<title>Optimizing agent system prompts with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21435</link>
<guid>https://news.jatlink.uk/21435</guid>
<description><![CDATA[ AgentCore optimization turns production traces into proposed configuration changes, then validates them before promotion. This technical companion to the launch post explains how the system prompt optimizer&#039;s reflector engine works and shares benchmark results for the Single Agent and Sub-Agent Reflectors. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/09/ML-21426-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 16 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Optimizing, agent, system, prompts, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Build a serverless PII redaction pipeline with Amazon Bedrock Data Automation</title>
<link>https://news.jatlink.uk/21436</link>
<guid>https://news.jatlink.uk/21436</guid>
<description><![CDATA[ Learn how to automate end-to-end PII detection and redaction from scanned documents at scale using Amazon Bedrock Data Automation with a custom blueprint, AWS Step Functions, and AWS Lambda. A custom blueprint redacts sensitive fields with field-level precision, and a token matching quality check raises recall across degraded and handwritten documents. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/11/ML-20554-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 16 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, serverless, PII, redaction, pipeline, with, Amazon, Bedrock, Data, Automation</media:keywords>
</item>

<item>
<title>Announcing instance preference lists for Amazon SageMaker AI training jobs</title>
<link>https://news.jatlink.uk/21343</link>
<guid>https://news.jatlink.uk/21343</guid>
<description><![CDATA[ Amazon SageMaker AI now offers instance preference lists for training and processing jobs. Specify an ordered list of up to five instance types, and SageMaker AI automatically launches on the first type with available capacity, eliminating manual retry loops and capacity-watching scripts. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/ML-21790-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 15 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Announcing, instance, preference, lists, for, Amazon, SageMaker, training, jobs</media:keywords>
</item>

<item>
<title>Optimizing cost and latency with Amazon Bedrock prompt caching</title>
<link>https://news.jatlink.uk/21341</link>
<guid>https://news.jatlink.uk/21341</guid>
<description><![CDATA[ Prompt caching in Amazon Bedrock can cut input token costs by up to 90% when you repeatedly send the same context to foundation models. This post walks through six practical prompt caching scenarios using the Converse API: message content, system prompt, tool definition, mixed TTL, tenant isolation, and LangChain integration. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/11/ML-20790-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 15 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Optimizing, cost, and, latency, with, Amazon, Bedrock, prompt, caching</media:keywords>
</item>

<item>
<title>Build an AI&amp;powered product tagging system with Amazon SageMaker serverless model customization</title>
<link>https://news.jatlink.uk/21342</link>
<guid>https://news.jatlink.uk/21342</guid>
<description><![CDATA[ Manually tagging thousands of catalog products is slow and inconsistent. This walkthrough shows how to customize Qwen3-8B with supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) on Amazon SageMaker serverless model customization, then deploy it for asynchronous inference to build a cost-efficient product tagging system. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/11/ML-20331-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 15 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, AI-powered, product, tagging, system, with, Amazon, SageMaker, serverless, model, customization</media:keywords>
</item>

<item>
<title>Abnormal AI: Amazon Bedrock AgentCore for agentic email security at scale</title>
<link>https://news.jatlink.uk/21290</link>
<guid>https://news.jatlink.uk/21290</guid>
<description><![CDATA[ Learn how Abnormal AI deployed Amazon Bedrock AgentCore Code Interpreter as an ephemeral compute scratch pad for the agents behind its real-time email threat detection at billion-message scale, plus the sandbox design decisions and practical lessons for builders deploying Code Interpreter in production. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/11/ML-21301-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 15 Sep 2026 02:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Abnormal, AI:, Amazon, Bedrock, AgentCore, for, agentic, email, security, scale</media:keywords>
</item>

<item>
<title>Manage end&amp;user OAuth consent for AI agents with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21272</link>
<guid>https://news.jatlink.uk/21272</guid>
<description><![CDATA[ Amazon Bedrock AgentCore Identity now offers a Consent portal, a managed web experience and session binding endpoint for AgentCore Gateway. This post walks through provisioning a portal, configuring GitHub and Slack 3LO targets, and the end-user consent flow, and shows how to review activity in AWS CloudTrail. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/14/ML-21874-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 14 Sep 2026 22:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Manage, end-user, OAuth, consent, for, agents, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>The generative AI customization spectrum: From prompt engineering to custom models on AWS</title>
<link>https://news.jatlink.uk/21257</link>
<guid>https://news.jatlink.uk/21257</guid>
<description><![CDATA[ Pick the right generative AI customization approach on AWS with an 8-step decision framework, from prompt engineering and RAG to fine-tuning, continued pre-training, and Amazon Nova Forge. Start simple and escalate only when you must. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/09/ML-21197-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 14 Sep 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>The, generative, customization, spectrum:, From, prompt, engineering, custom, models, AWS</media:keywords>
</item>

<item>
<title>Automate replenishment with MMF, Databricks Genie, and Amazon Quick</title>
<link>https://news.jatlink.uk/21258</link>
<guid>https://news.jatlink.uk/21258</guid>
<description><![CDATA[ Foundation models made catalog-wide demand forecasting easy; the hard part is now acting on the forecast. This post builds a closed detect-decide-act loop on Databricks and Amazon Quick that reconciles demand surges against live supplier availability and places replenishment orders unattended, escalating to a human only when no supplier can cover a surge. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/28/ML-21670-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 14 Sep 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, replenishment, with, MMF, Databricks, Genie, and, Amazon, Quick</media:keywords>
</item>

<item>
<title>How Ninth Wave built AI&amp;powered open finance onboarding on Amazon Bedrock</title>
<link>https://news.jatlink.uk/21256</link>
<guid>https://news.jatlink.uk/21256</guid>
<description><![CDATA[ Learn how Ninth Wave built Compass, a multi-agent AI onboarding assistant on Amazon Bedrock AgentCore that validates bank APIs against Financial Data Exchange (FDX) standards, scores compliance, and compresses open finance onboarding from weeks to minutes while meeting SOC 2 and PCI DSS requirements. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/13/ML-21160-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 14 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Ninth, Wave, built, AI-powered, open, finance, onboarding, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Build interactive MCP Apps using Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/21046</link>
<guid>https://news.jatlink.uk/21046</guid>
<description><![CDATA[ Learn how to build and deploy an MCP App with interactive HTML widgets on Amazon Bedrock AgentCore. Because MCP Apps is a host-agnostic standard, the same server delivers the same rich experience across AI hosts like ChatGPT and Claude that support the extension. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/09/ML-20314-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 11 Sep 2026 22:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, interactive, MCP, Apps, using, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Monitoring production agent lifecycle with AWS DevOps Agent and AgentCore Evaluations</title>
<link>https://news.jatlink.uk/21044</link>
<guid>https://news.jatlink.uk/21044</guid>
<description><![CDATA[ Multi-agent systems fail in ways traditional monitoring misses. This post presents a dual-layer approach to monitoring production agents: Amazon Bedrock AgentCore Evaluations for continuous quality scoring and AWS DevOps Agent for autonomous infrastructure investigation, shown on a four-agent airline reservation system. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20434/blogpost_eval_video.mp4" length="49398" type="image/jpeg"/>
<pubDate>Fri, 11 Sep 2026 22:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Monitoring, production, agent, lifecycle, with, AWS, DevOps, Agent, and, AgentCore, Evaluations</media:keywords>
</item>

<item>
<title>Beyond the price per token: Choosing the right OpenAI model on Amazon Bedrock for your workload</title>
<link>https://news.jatlink.uk/21045</link>
<guid>https://news.jatlink.uk/21045</guid>
<description><![CDATA[ Comparing models on dollars per million tokens misses what production workloads actually pay for: outcomes. This post shares an open-source benchmarking harness that measures cost per correct answer, agent trajectory cost, and rubric-graded deliverable quality across OpenAI models on Amazon Bedrock. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/09/ML-21634-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 11 Sep 2026 22:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Beyond, the, price, per, token:, Choosing, the, right, OpenAI, model, Amazon, Bedrock, for, your, workload</media:keywords>
</item>

<item>
<title>Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0</title>
<link>https://news.jatlink.uk/20971</link>
<guid>https://news.jatlink.uk/20971</guid>
<description><![CDATA[ TwelveLabs Marengo Embed 3.0 is now generally available as an embedding model in Amazon Bedrock Knowledge Bases, bringing fully managed natural language search to video, image, and audio content. This walkthrough shows how to build a knowledge base powered by Marengo 3.0 and run semantic queries against your media. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/10/ML-21835-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 11 Sep 2026 02:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Video, and, image, search, Amazon, Bedrock, Knowledge, Base, using, Marengo, 3.0</media:keywords>
</item>

<item>
<title>Reduce LLM latency with prefix&amp;aware routing on Amazon SageMaker Inference</title>
<link>https://news.jatlink.uk/20969</link>
<guid>https://news.jatlink.uk/20969</guid>
<description><![CDATA[ Amazon SageMaker Inference now offers prefix-aware routing, a routing strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. In benchmarks on Llama 3.1 70B, it reduced P50 time-to-first-token by up to 77% and raised KV cache hit rates from about 25% to over 80%. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/10/ML-21885-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 11 Sep 2026 02:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reduce, LLM, latency, with, prefix-aware, routing, Amazon, SageMaker, Inference</media:keywords>
</item>

<item>
<title>Reduce inference cold starts on Amazon SageMaker HyperPod with model caching</title>
<link>https://news.jatlink.uk/20970</link>
<guid>https://news.jatlink.uk/20970</guid>
<description><![CDATA[ Amazon SageMaker HyperPod now supports model caching for inference, which pre-loads model weights and container images onto cluster nodes so pods read from local NVMe storage instead of downloading over the network. Learn how model caching cuts cold starts from tens of minutes to seconds, how it works, and how to enable it. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/ML-21820-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 11 Sep 2026 02:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reduce, inference, cold, starts, Amazon, SageMaker, HyperPod, with, model, caching</media:keywords>
</item>

<item>
<title>Amazon Quick is now generally available on desktop</title>
<link>https://news.jatlink.uk/20951</link>
<guid>https://news.jatlink.uk/20951</guid>
<description><![CDATA[ Your teams get an AI assistant that handles real work while your data stays in your environment and your conversations stay private Today, the Amazon Quick desktop application is generally available on macOS and Windows. We’re also adding a new activity feed to the mobile experience on iOS and Android that consolidates email, calendar, CRM, […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/10/Amazon-Quick-is-now-generally-available-on-desktop.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 10 Sep 2026 22:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Quick, now, generally, available, desktop</media:keywords>
</item>

<item>
<title>Model&amp;agnostic PII detection with LLMs</title>
<link>https://news.jatlink.uk/20932</link>
<guid>https://news.jatlink.uk/20932</guid>
<description><![CDATA[ A configurable, model-agnostic detector that turns any large language model on Amazon Bedrock into a PII detector. Because the entities to detect live in a prompt rather than in code, one detector adapts to new entity types without retraining, and it outperforms an off-the-shelf tool across five public corpora and nine LLM-based detectors. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/ML-21255-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 10 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Model-agnostic, PII, detection, with, LLMs</media:keywords>
</item>

<item>
<title>Build an end&amp;to&amp;end RFI questionnaire workflow using Amazon Quick Automate</title>
<link>https://news.jatlink.uk/20931</link>
<guid>https://news.jatlink.uk/20931</guid>
<description><![CDATA[ Learn how to build an end-to-end RFI questionnaire workflow with Amazon Quick Automate. Read a multi-tab RFI workbook from Amazon S3, use natural-language prompts to extract and structure the questionnaire data, refine the workflow through conversation, and write clean CSV output back to Amazon S3 — cutting development from days to hours. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/09/ML-20411-featured-image-1.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 10 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, end-to-end, RFI, questionnaire, workflow, using, Amazon, Quick, Automate</media:keywords>
</item>

<item>
<title>Agent Evaluation Metric for multi&amp;turn conversations</title>
<link>https://news.jatlink.uk/20933</link>
<guid>https://news.jatlink.uk/20933</guid>
<description><![CDATA[ Multi-turn agents fail in ways single-turn evaluation misses: one early mistake corrupts every later turn. This post introduces the Agent Evaluation Metric (AEM), a decomposable, turn-level way to measure agent quality, applied to its first dimension, correctness, to pinpoint the turn that caused a failure and separate it from the turns that inherited it. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-20819-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 10 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agent, Evaluation, Metric, for, multi-turn, conversations</media:keywords>
</item>

<item>
<title>How AvioBook builds turnaround insights from operational data with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/20934</link>
<guid>https://news.jatlink.uk/20934</guid>
<description><![CDATA[ AvioBook, a Thales Group Company, prototyped Connected Analytics on Amazon Bedrock AgentCore to turn AvioBook Connect&#039;s operational data into plain-language, evidence-based answers for airline managers and dispatchers, helping them find and act on the causes of flight turnaround delays. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/13/ML-21410-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 10 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, AvioBook, builds, turnaround, insights, from, operational, data, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Deploying Qwen3.8&amp;2.4T&amp;A95B on Amazon SageMaker HyperPod with vLLM</title>
<link>https://news.jatlink.uk/20862</link>
<guid>https://news.jatlink.uk/20862</guid>
<description><![CDATA[ Learn how to deploy Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter open-weight model, on Amazon SageMaker HyperPod with vLLM. This walkthrough covers cluster provisioning, NVFP4 quantization, and an OpenAI-compatible endpoint with built-in reasoning, tool calling, and native MTP speculative decoding. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/09/ML-21725-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 10 Sep 2026 02:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploying, Qwen3.8-2.4T-A95B, Amazon, SageMaker, HyperPod, with, vLLM</media:keywords>
</item>

<item>
<title>ICYMI: What landed for AI builders in August 2026</title>
<link>https://news.jatlink.uk/20847</link>
<guid>https://news.jatlink.uk/20847</guid>
<description><![CDATA[ A recap of August 2026 launches for AI builders across Amazon Bedrock, Amazon Bedrock AgentCore, and Strands: million-token context for OpenAI models, cross-Region inference, agents that run for up to 14 days on dedicated compute, expanded AWS GovCloud availability, and Strands Robots for physical deployment. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/ML-21781-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 09 Sep 2026 22:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>ICYMI:, What, landed, for, builders, August, 2026</media:keywords>
</item>

<item>
<title>How Heurist Finance built an AI&amp;native investment workbench on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/20848</link>
<guid>https://news.jatlink.uk/20848</guid>
<description><![CDATA[ Learn how Heurist built Heurist Finance, a conversational AI investment workbench, on Amazon Bedrock AgentCore. This customer story shows how AgentCore payments, Identity, Memory, Code Interpreter, and Observability let a small team buy premium market data per query, isolate analysis in a sandbox, and keep every action auditable. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/27/ML-21623-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 09 Sep 2026 22:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Heurist, Finance, built, AI-native, investment, workbench, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Simplify and support your TorchServe workloads using Ray Serve Deep Learning Containers</title>
<link>https://news.jatlink.uk/20827</link>
<guid>https://news.jatlink.uk/20827</guid>
<description><![CDATA[ TorchServe is no longer maintained, leaving teams to own the entire GPU inference stack. The AWS Ray Serve Deep Learning Container is a supported, pre-tested container with the framework, GPU drivers, and serving layer already assembled. This post walks through deploying a vision-language model on Amazon EKS using the Ray Serve DLC on a single GPU node. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/ML-21647-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 09 Sep 2026 18:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Simplify, and, support, your, TorchServe, workloads, using, Ray, Serve, Deep, Learning, Containers</media:keywords>
</item>

<item>
<title>Automate user&amp;level custom permissions for Amazon Quick</title>
<link>https://news.jatlink.uk/20828</link>
<guid>https://news.jatlink.uk/20828</guid>
<description><![CDATA[ Amazon Quick custom permissions let you enforce least-privilege access by toggling features per user. This post walks through four patterns to automate custom permissions across the user lifecycle: a RegisterUser API parameter, account and role defaults, event-driven Amazon EventBridge and AWS Lambda automation, and a retroactive batch update script. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/ML-21102-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 09 Sep 2026 18:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, user-level, custom, permissions, for, Amazon, Quick</media:keywords>
</item>

<item>
<title>Take on your most ambitious work with GPT&amp;6 Astra on Amazon Bedrock</title>
<link>https://news.jatlink.uk/20763</link>
<guid>https://news.jatlink.uk/20763</guid>
<description><![CDATA[ GPT-6 Astra from OpenAI is now generally available on Amazon Bedrock. It brings deeper reasoning and sharper judgment to your most demanding tasks, running on the Amazon Bedrock inference engine built for high performance, security, and scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21849-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 09 Sep 2026 02:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Take, your, most, ambitious, work, with, GPT-6, Astra, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Amazon SageMaker Feature Store introduces UpdateRecord for feature&amp;level writes</title>
<link>https://news.jatlink.uk/20743</link>
<guid>https://news.jatlink.uk/20743</guid>
<description><![CDATA[ Amazon SageMaker Feature Store now supports feature-level writes. With the new UpdateRecord API, you can update one or more feature values in a single call without reading or rewriting the entire record. It is available for both the Standard (Amazon DynamoDB) and In-Memory (Amazon ElastiCache) online store tiers. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/08/Amazon-SageMaker-Feature-Store-introduces-UpdateRecord-for-feature-level-writes.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, SageMaker, Feature, Store, introduces, UpdateRecord, for, feature-level, writes</media:keywords>
</item>

<item>
<title>Govern models with MLflow and Amazon SageMaker AI Model Registry sync: Part 2</title>
<link>https://news.jatlink.uk/20744</link>
<guid>https://news.jatlink.uk/20744</guid>
<description><![CDATA[ Governing models across accounts is the next step after automatic model registration. This post extends managed MLflow and Amazon SageMaker AI Model Registry sync to two cross-account governance topologies: a hub-and-spoke pattern that centralizes governance with AWS RAM, and a hybrid pattern that keeps development accounts isolated. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-21407-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Govern, models, with, MLflow, and, Amazon, SageMaker, Model, Registry, sync:, Part</media:keywords>
</item>

<item>
<title>Govern models with MLflow and Amazon SageMaker AI Model Registry sync: Part 1</title>
<link>https://news.jatlink.uk/20745</link>
<guid>https://news.jatlink.uk/20745</guid>
<description><![CDATA[ Managed MLflow on Amazon SageMaker AI now syncs richer model metadata (training metrics, evaluation results, inference specs, and lineage) into the SageMaker AI Model Registry, with lifecycle stage promotion. Part 1 shows how to govern candidate models in a single account using IAM guardrails. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-21407-featured-image-1.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Govern, models, with, MLflow, and, Amazon, SageMaker, Model, Registry, sync:, Part</media:keywords>
</item>

<item>
<title>Pathway’s brain&amp;inspired architecture development on Amazon SageMaker HyperPod</title>
<link>https://news.jatlink.uk/20742</link>
<guid>https://news.jatlink.uk/20742</guid>
<description><![CDATA[ Pathway&#039;s Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought tokens. See how Pathway develops and scales BDH on Amazon SageMaker HyperPod, and how BDH-CQ set a new cost-efficiency mark on the ARC-AGI-1 benchmark. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/ML-21697-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 22:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Pathway’s, brain-inspired, architecture, development, Amazon, SageMaker, HyperPod</media:keywords>
</item>

<item>
<title>How HPE Zerto built an agentic troubleshooting system with Amazon Bedrock</title>
<link>https://news.jatlink.uk/20719</link>
<guid>https://news.jatlink.uk/20719</guid>
<description><![CDATA[ HPE Zerto built an agentic troubleshooting system powered by Amazon Bedrock that runs on-premises inside the customer environment. This post describes the multi-agent architecture, the on-premises deployment model built with Strands Agents, and the engineering challenges of grounding agents in live disaster recovery data. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/01/ML-20849-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, HPE, Zerto, built, agentic, troubleshooting, system, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How DiDi built intelligent contact center QA with Amazon Bedrock</title>
<link>https://news.jatlink.uk/20720</link>
<guid>https://news.jatlink.uk/20720</guid>
<description><![CDATA[ DiDi built a transparent, self-owned contact center quality assurance (QA) system on Amazon Bedrock, replacing an opaque third-party tool. Intent verification accuracy rose from 38% to 86%, compliance scoring topped 90%, and Voice of Customer trend analysis dropped from hours to minutes across Spanish and Portuguese support. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-21371-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, DiDi, built, intelligent, contact, center, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Automated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions</title>
<link>https://news.jatlink.uk/20717</link>
<guid>https://news.jatlink.uk/20717</guid>
<description><![CDATA[ Wire Amazon Bedrock AgentCore Evaluations into a GitHub Actions pipeline: deploy an AI agent and an OAuth-protected MCP server to AgentCore runtime, invoke the agent with test prompts, score the responses, and automatically block pull requests when agent behavior regresses. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/28/ML-20711-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automated, agent, evaluation, with, Amazon, Bedrock, AgentCore, and, GitHub, Actions</media:keywords>
</item>

<item>
<title>Benchmarking small LLM inference on SageMaker AI: G7 vs G5 and G6</title>
<link>https://news.jatlink.uk/20718</link>
<guid>https://news.jatlink.uk/20718</guid>
<description><![CDATA[ Benchmark two 30B Mixture-of-Experts models, Qwen3-Coder-30B and NVIDIA Nemotron-3-Nano-30B, across G5, G6, G6e, and G7 GPU instances on Amazon SageMaker AI. Compare throughput, latency, and cost-per-token, and see how G7&#039;s NVIDIA Blackwell GPUs deliver measurable price-performance gains for real-time LLM inference. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/ML-21730-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 08 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Benchmarking, small, LLM, inference, SageMaker, AI:, and</media:keywords>
</item>

<item>
<title>Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/20448</link>
<guid>https://news.jatlink.uk/20448</guid>
<description><![CDATA[ Learn how to deploy a multimodal WhatsApp ordering assistant that takes customer orders through text, voice notes, and real-time voice calls on a single business number, built on Amazon Bedrock AgentCore with Amazon Nova 2. The channel and ordering layers stay separate, and one shared memory recognizes each customer across all three channels. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Sat, 05 Sep 2026 02:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploy, multimodal, WhatsApp, ordering, assistant, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Designing lifecycle policies for AgentCore memory</title>
<link>https://news.jatlink.uk/20431</link>
<guid>https://news.jatlink.uk/20431</guid>
<description><![CDATA[ Long-running AI agents accumulate outdated memories that degrade quality and create compliance risk. Learn how to design memory lifecycle policies for Amazon Bedrock AgentCore: scoring, consolidating, and pruning agent memories on a nightly AWS Step Functions workflow, with a deployable AWS CDK stack. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/26/ML-20851-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 04 Sep 2026 22:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Designing, lifecycle, policies, for, AgentCore, memory</media:keywords>
</item>

<item>
<title>Run agent&amp;driven Amazon SageMaker HyperPod operations with InstantStart</title>
<link>https://news.jatlink.uk/20410</link>
<guid>https://news.jatlink.uk/20410</guid>
<description><![CDATA[ HyperPod InstantStart is an open source control plane that composes Amazon EKS orchestration with the managed capabilities of Amazon SageMaker HyperPod. It drives the same guarded operations through both a web interface and an AI agent, turning cluster bootstrap, capacity, training, inference, and storage into dependable, agent-driven infrastructure. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/26/ML-21539-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 04 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Run, agent-driven, Amazon, SageMaker, HyperPod, operations, with, InstantStart</media:keywords>
</item>

<item>
<title>Customizing your knowledge base on Amazon Bedrock for large and complex documents using Amazon Textract</title>
<link>https://news.jatlink.uk/20411</link>
<guid>https://news.jatlink.uk/20411</guid>
<description><![CDATA[ Learn how to customize an Amazon Bedrock knowledge base for large, complex documents by combining the high-accuracy text extraction of Amazon Textract with the generative AI of Amazon Bedrock. This post shows how to ingest and preprocess PDFs and images, then query utility bills at scale for faster, more accurate customer interactions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-18730-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 04 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Customizing, your, knowledge, base, Amazon, Bedrock, for, large, and, complex, documents, using, Amazon, Textract</media:keywords>
</item>

<item>
<title>How Intuit built an agentic disaster recovery assistant with Amazon Bedrock</title>
<link>https://news.jatlink.uk/20412</link>
<guid>https://news.jatlink.uk/20412</guid>
<description><![CDATA[ Disaster recovery at scale is hard. Learn how Intuit built EWOK Agent, an agentic disaster recovery assistant on Amazon Bedrock that lets on-call engineers run production failovers from a plain-language request while keeping every action audited, policy-compliant, and safe. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/ML-21646-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 04 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Intuit, built, agentic, disaster, recovery, assistant, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod</title>
<link>https://news.jatlink.uk/20409</link>
<guid>https://news.jatlink.uk/20409</guid>
<description><![CDATA[ Building a Physical AI system takes a continuous pipeline, not a single training job. This post shows how to run that model factory (synthetic data generation, post-training, and closed-loop evaluation with NVIDIA Cosmos 3) on a persistent, resilient Amazon SageMaker HyperPod cluster on Amazon EKS, with GPU goodput as the metric that matters. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-21222-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 04 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, Physical, model, factory, with, NVIDIA, Cosmos, SageMaker, HyperPod</media:keywords>
</item>

<item>
<title>Embed Quick Sight visuals using Cognito user authentication</title>
<link>https://news.jatlink.uk/20310</link>
<guid>https://news.jatlink.uk/20310</guid>
<description><![CDATA[ Learn how to embed individual Amazon Quick Sight visuals into a React application with per-user access control. This walkthrough uses Amazon Cognito authentication and a serverless AWS Lambda backend to generate scoped embed URLs, deployed with a single AWS CloudFormation stack. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/27/ML-20784-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 03 Sep 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Embed, Quick, Sight, visuals, using, Cognito, user, authentication</media:keywords>
</item>

<item>
<title>Set up OpenAI ChatGPT Codex with LiteLLM on Amazon ECS and Amazon Bedrock</title>
<link>https://news.jatlink.uk/20308</link>
<guid>https://news.jatlink.uk/20308</guid>
<description><![CDATA[ Deploy a customer-operated LiteLLM gateway on Amazon ECS with AWS Fargate, connect it to an OpenAI model on Amazon Bedrock, and configure Codex to route requests through the gateway&#039;s Responses API with scoped identities, budgets, rate limits, and telemetry. We also compare direct IAM Identity Center access and a managed Portkey deployment. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/01/ML-21675-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 03 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Set, OpenAI, ChatGPT, Codex, with, LiteLLM, Amazon, ECS, and, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Best practices for building agentic automations with Amazon Quick Automate</title>
<link>https://news.jatlink.uk/20309</link>
<guid>https://news.jatlink.uk/20309</guid>
<description><![CDATA[ Learn best practices for building production-grade, agent-based business process automations with Amazon Quick Automate: choosing the right process, designing focused agents, combining them with deterministic steps, applying human-in-the-loop review, and building in evaluation and observability. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/26/ML-21394-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 03 Sep 2026 18:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Best, practices, for, building, agentic, automations, with, Amazon, Quick, Automate</media:keywords>
</item>

<item>
<title>Migrate agentic workloads to Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/20306</link>
<guid>https://news.jatlink.uk/20306</guid>
<description><![CDATA[ An agent that works in a notebook is not an agent in production. This post walks through migrating a LangGraph customer support agent to Amazon Bedrock AgentCore in two stages: onto Runtime, Gateway, and Memory, then to model-driven planning on Strands Agents, retiring operational burdens along the way. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-20753-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 03 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Migrate, agentic, workloads, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Integrating Outlook with Amazon Quick for AI&amp;powered email automation</title>
<link>https://news.jatlink.uk/20307</link>
<guid>https://news.jatlink.uk/20307</guid>
<description><![CDATA[ Integrate Microsoft Outlook with Amazon Quick to automate email management, calendar scheduling, and workflow coordination. This post walks through the end-to-end setup and shows automation scenarios using Amazon Quick chat agents, Amazon Quick Flows, and Amazon Quick Automate. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/24/ML-20379-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 03 Sep 2026 18:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Integrating, Outlook, with, Amazon, Quick, for, AI-powered, email, automation</media:keywords>
</item>

<item>
<title>AI&amp;driven development lifecycle using Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/20305</link>
<guid>https://news.jatlink.uk/20305</guid>
<description><![CDATA[ Engineering teams adopting the AI-Driven Development Lifecycle (AI-DLC) often struggle to turn concepts into working code. This post walks through two reference implementations on Amazon Bedrock AgentCore, Kiro, and Claude Code: an SQL-to-ER-diagram generator and a multi-agent code security analyzer that put the AI-DLC construction phase into practice. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-21366-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 03 Sep 2026 18:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AI-driven, development, lifecycle, using, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Accessing OpenAI models on Amazon Bedrock from Australia with global cross&amp;Region inference</title>
<link>https://news.jatlink.uk/20249</link>
<guid>https://news.jatlink.uk/20249</guid>
<description><![CDATA[ Australian teams can now access OpenAI GPT-5.6 Sol, Terra, and Luna models on Amazon Bedrock with global cross-Region inference from the Asia Pacific (Sydney) and Asia Pacific (Melbourne) Regions. This post shows how to invoke the models, use prompt caching, set up Codex with OpenID Connect authentication, and monitor usage with Amazon CloudWatch. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/Accessing-OpenAI-models-on-Amazon-Bedrock-from-Australia-with-global-cross-Region-inference.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 03 Sep 2026 02:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accessing, OpenAI, models, Amazon, Bedrock, from, Australia, with, global, cross-Region, inference</media:keywords>
</item>

<item>
<title>Trinity: Agentic AI&amp;powered transition planning for students with disabilities</title>
<link>https://news.jatlink.uk/20230</link>
<guid>https://news.jatlink.uk/20230</guid>
<description><![CDATA[ Learn how University Startups and its AWS partner g/d/n/a scaled Trinity, a conversational AI solution for students with disabilities, into a serverless multi-agent architecture on Amazon Bedrock that produces IDEA-aligned transition plans for school districts across the US. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/ML-20631-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 02 Sep 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Trinity:, Agentic, AI-powered, transition, planning, for, students, with, disabilities</media:keywords>
</item>

<item>
<title>How an AWS team detects dashboard content failures at scale using Amazon Bedrock</title>
<link>https://news.jatlink.uk/20228</link>
<guid>https://news.jatlink.uk/20228</guid>
<description><![CDATA[ Business intelligence dashboards can fail silently, showing blank, stale, or wrong data even when every infrastructure monitor reports healthy. Learn how an AWS team built an automated, AI-powered content validation solution on Amazon Bedrock that scans hundreds of dashboards and alerts owners, cutting mean time to detection from days to under an hour. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-21432-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 02 Sep 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, AWS, team, detects, dashboard, content, failures, scale, using, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>From code to diagrams: Agentic architecture documentation with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/20229</link>
<guid>https://news.jatlink.uk/20229</guid>
<description><![CDATA[ Learn how a global interdealer broker built an automated architecture documentation pipeline on Amazon Bedrock AgentCore that analyzes .NET code bases, generates architecture diagrams, and maintains searchable documentation through Amazon Bedrock Knowledge Bases and AWS CodePipeline. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/28/ML-20745-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 02 Sep 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, code, diagrams:, Agentic, architecture, documentation, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Modernizing and scaling support operations with generative AI on AWS</title>
<link>https://news.jatlink.uk/20227</link>
<guid>https://news.jatlink.uk/20227</guid>
<description><![CDATA[ Learn how to build a generative AI-based support operations platform on AWS that converts training videos into structured SOPs, applies Retrieval-Augmented Generation to guide ticket resolution, and uses machine learning to predict SLA risk and prioritize work. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/27/ML-20585-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 02 Sep 2026 22:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Modernizing, and, scaling, support, operations, with, generative, AWS</media:keywords>
</item>

<item>
<title>Introducing Claude Fable 5.1 on AWS</title>
<link>https://news.jatlink.uk/20149</link>
<guid>https://news.jatlink.uk/20149</guid>
<description><![CDATA[ Claude Fable 5.1 is now available on Amazon Bedrock and Claude Platform on AWS. This post covers Claude Fable 5.1&#039;s improvements, the Enterprise Frontier Safeguards for keeping your data in a cloud environment you control, and how to start building with the model on Amazon Bedrock. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/01/ml-21797.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 22:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Claude, Fable, 5.1, AWS</media:keywords>
</item>

<item>
<title>How Boomi Scribe streamlines documentation using AWS</title>
<link>https://news.jatlink.uk/20128</link>
<guid>https://news.jatlink.uk/20128</guid>
<description><![CDATA[ Boomi Scribe is an AI-powered agent on AWS that automatically generates documentation for enterprise integration workflows. Learn how Boomi uses Amazon Bedrock, Amazon SageMaker AI, Amazon S3, Amazon DynamoDB, and AWS Lambda to parse integration DAGs, generate detailed documentation, and compare component versions at scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/11/ML-19052-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 18:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Boomi, Scribe, streamlines, documentation, using, AWS</media:keywords>
</item>

<item>
<title>How ZS democratized secure ad&amp;hoc analytics with Amazon SageMaker</title>
<link>https://news.jatlink.uk/20127</link>
<guid>https://news.jatlink.uk/20127</guid>
<description><![CDATA[ Learn how ZS built a security-hardened Amazon SageMaker platform that balances developer agility with healthcare-grade governance, serving 1,000+ daily active users across 200+ SageMaker domains. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/21/ML-20828-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, democratized, secure, ad-hoc, analytics, with, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>From theory to delivery: How Atos upskilled 400 engineers in agentic AI</title>
<link>https://news.jatlink.uk/20123</link>
<guid>https://news.jatlink.uk/20123</guid>
<description><![CDATA[ When Atos set out to upskill 400 engineers in agentic AI, hands-on learning was the missing ingredient. Over three days, engineers built multi-agent systems on AWS through an AI League event. This post explains why Atos chose the format, what engineers built and learned, and what other enterprises should consider. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/28/ML-21185-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, theory, delivery:, How, Atos, upskilled, 400, engineers, agentic</media:keywords>
</item>

<item>
<title>Tokenomics at scale: How Jamf built real&amp;time spend enforcement for Amazon Bedrock</title>
<link>https://news.jatlink.uk/20124</link>
<guid>https://news.jatlink.uk/20124</guid>
<description><![CDATA[ As generative AI adoption scales, cost governance becomes a top challenge. Learn how Jamf built real-time, per-user spend enforcement for Amazon Bedrock using IAM Customer Managed Policies, an Amazon Athena cost view, and a serverless AWS Lambda loop that applies tiered model limits in near-real-time without disrupting active sessions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/28/ML-21656-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Tokenomics, scale:, How, Jamf, built, real-time, spend, enforcement, for, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Securing Amazon Quick from POC to production: Agents, Flows, and Spaces</title>
<link>https://news.jatlink.uk/20125</link>
<guid>https://news.jatlink.uk/20125</guid>
<description><![CDATA[ Amazon Quick proof-of-concept projects often stall when security teams review the production plan. This post walks through designing dashboards, Spaces, knowledge bases, agents, and Flows with security controls that hold as you scale: dataset shaping, agent isolation, document classification, and approval gates. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/21/ML-21604-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Securing, Amazon, Quick, from, POC, production:, Agents, Flows, and, Spaces</media:keywords>
</item>

<item>
<title>How t54 built a trust layer with Amazon Bedrock AgentCore payments</title>
<link>https://news.jatlink.uk/20126</link>
<guid>https://news.jatlink.uk/20126</guid>
<description><![CDATA[ t54 built x402-secure, a trust layer on Amazon Bedrock AgentCore payments that scores every endpoint before an autonomous agent pays it. See how session budgets, credential isolation, and a deterministic trust gate have governed more than 20 million agent-initiated transactions with no human in the loop. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21104/agentcorepayment-x402-secure-demo.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, t54, built, trust, layer, with, Amazon, Bedrock, AgentCore, payments</media:keywords>
</item>

<item>
<title>Connect an AgentCore Runtime hosted MCP server to Amazon Quick</title>
<link>https://news.jatlink.uk/20076</link>
<guid>https://news.jatlink.uk/20076</guid>
<description><![CDATA[ In this post, you will learn how to deploy and host your MCP server in AgentCore Runtime and integrate it with Amazon Quick, along with the prerequisites. With this pattern, you promote reusability and avoid duplication of AI tools, so clients can reuse commonly used tools and agents exposed through an MCP server instead of authoring them from scratch again. Your customers get a way to use your product inside Amazon Quick (chat agents and workflows) without building custom connectors for every use case. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/08/20742.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 01 Sep 2026 02:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Connect, AgentCore, Runtime, hosted, MCP, server, Amazon, Quick</media:keywords>
</item>

<item>
<title>Build observable enterprise agentic retrieval using Managed Amazon Bedrock Knowledge Base with AWS CloudFormation</title>
<link>https://news.jatlink.uk/20063</link>
<guid>https://news.jatlink.uk/20063</guid>
<description><![CDATA[ This post builds an enterprise agentic retrieval solution on the Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore. An agent reasons, routes across multiple knowledge bases, and returns cited answers, with seven layers of observability and both on-demand and continuous evaluation, all deployed with a single AWS CloudFormation chain. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/27/ML-21427-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 31 Aug 2026 22:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, observable, enterprise, agentic, retrieval, using, Managed, Amazon, Bedrock, Knowledge, Base, with, AWS, CloudFormation</media:keywords>
</item>

<item>
<title>Build multi&amp;tenant agentic chat applications on enterprise data with Amazon Bedrock Managed Knowledge Base</title>
<link>https://news.jatlink.uk/20064</link>
<guid>https://news.jatlink.uk/20064</guid>
<description><![CDATA[ Learn how to build a multi-tenant agentic document chat application on Amazon Bedrock Managed Knowledge Base, where users upload documents and immediately ask grounded questions. This post covers the ingestion and retrieval flows, the asynchronous indexing lifecycle, per-user data isolation, and best practices for operating the solution at scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/27/ML-21312-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 31 Aug 2026 22:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, multi-tenant, agentic, chat, applications, enterprise, data, with, Amazon, Bedrock, Managed, Knowledge, Base</media:keywords>
</item>

<item>
<title>Manage agents, tools and skills at scale with AWS Agent Registry</title>
<link>https://news.jatlink.uk/20062</link>
<guid>https://news.jatlink.uk/20062</guid>
<description><![CDATA[ AWS Agent Registry is now generally available: a single, searchable, governed catalog for the agents, tools, skills, and custom resources across your organization. This post explains what Registry is and walks through its publishing, curation, and discovery workflows, plus enterprise considerations and what&#039;s next. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/31/ML-20739-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 31 Aug 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Manage, agents, tools, and, skills, scale, with, AWS, Agent, Registry</media:keywords>
</item>

<item>
<title>AWS recognized as a Leader in The Forrester Wave: AI Infrastructure Solutions, Q4 2025</title>
<link>https://news.jatlink.uk/20061</link>
<guid>https://news.jatlink.uk/20061</guid>
<description><![CDATA[ We&#039;re excited to share that AWS has been recognized as a Leader in The Forrester Wave: AI Infrastructure Solutions, Q4 2025. In this evaluation of 13 providers, AWS received the highest score in the Strategy category. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/27/ML-21674-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 31 Aug 2026 22:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AWS, recognized, Leader, The, Forrester, Wave:, Infrastructure, Solutions, 2025</media:keywords>
</item>

<item>
<title>Batch write and discover records in Amazon SageMaker Feature Store</title>
<link>https://news.jatlink.uk/19859</link>
<guid>https://news.jatlink.uk/19859</guid>
<description><![CDATA[ Amazon SageMaker Feature Store now supports two new APIs: BatchWriteRecord writes up to 25 records across multiple feature groups in a single call, and ListRecords enumerates record identifiers within a feature group. In this post, we walk through each API with code examples you can use to get started. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/27/ML-21718-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 28 Aug 2026 22:00:21 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Batch, write, and, discover, records, Amazon, SageMaker, Feature, Store</media:keywords>
</item>

<item>
<title>How Decathlon runs demand forecasting at scale with Chronos&amp;2</title>
<link>https://news.jatlink.uk/19841</link>
<guid>https://news.jatlink.uk/19841</guid>
<description><![CDATA[ Decathlon, one of the world&#039;s largest sporting goods retailers, forecasts weekly demand for tens of thousands of products across multiple continents. Learn how they deployed Chronos-2 on AWS to improve forecast accuracy by 11-15 points while cutting operational complexity and running weekly inference for about $0.03 on CPU-only instances. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/24/ML-21294-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 28 Aug 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Decathlon, runs, demand, forecasting, scale, with, Chronos-2</media:keywords>
</item>

<item>
<title>Spreading the load: How Salesforce met Multi&amp;AZ HA with SageMaker Inference Components</title>
<link>https://news.jatlink.uk/19842</link>
<guid>https://news.jatlink.uk/19842</guid>
<description><![CDATA[ Learn how Salesforce used Amazon SageMaker AI Inference Component placement (the SchedulingConfig parameter) to distribute model copies across multiple Availability Zones, meeting their Multi-AZ high availability compliance requirements without sacrificing the cost efficiency of multi-model co-hosting. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/25/ML-20956-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 28 Aug 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Spreading, the, load:, How, Salesforce, met, Multi-AZ, with, SageMaker, Inference, Components</media:keywords>
</item>

<item>
<title>Build agentic creative workflows with Amazon Quick and fal</title>
<link>https://news.jatlink.uk/19787</link>
<guid>https://news.jatlink.uk/19787</guid>
<description><![CDATA[ Creative teams produce more assets than ever, but fragmented tools and manual context transfer slow production. This post shows how to build a reusable agent harness with Amazon Quick and fal, connected through the Model Context Protocol (MCP), using two hands-on workflows: an eight-panel storyboard and a music-video concept prototype. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-21711/video.mp4" length="49398" type="image/jpeg"/>
<pubDate>Fri, 28 Aug 2026 02:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, agentic, creative, workflows, with, Amazon, Quick, and, fal</media:keywords>
</item>

<item>
<title>Introducing OpenAI models on Amazon Bedrock for in&amp;country inferencing in India</title>
<link>https://news.jatlink.uk/19769</link>
<guid>https://news.jatlink.uk/19769</guid>
<description><![CDATA[ Amazon Bedrock now supports the OpenAI GPT-5.6 models, Terra and Luna, in India with India geographic cross-Region inference. If you have local data processing requirements, you can now use these models at scale while Amazon Bedrock keeps inference requests and data within India. ]]></description>
<enclosure url="http://news.jatlink.uk" length="4096" type="image/jpeg"/>
<pubDate>Thu, 27 Aug 2026 22:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, OpenAI, models, Amazon, Bedrock, for, in-country, inferencing, India</media:keywords>
</item>

<item>
<title>Deepgram deepens Amazon SageMaker AI observability with Enhanced Metrics</title>
<link>https://news.jatlink.uk/19749</link>
<guid>https://news.jatlink.uk/19749</guid>
<description><![CDATA[ Self-hosted speech AI carries an observability trade-off: the numbers that drive capacity planning and cost management stay locked inside the vendor container. Deepgram closes that gap on Amazon SageMaker AI with two capabilities that land billing, usage, and per-GPU metrics directly in your own Amazon CloudWatch account. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/21/ML-21597-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 27 Aug 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deepgram, deepens, Amazon, SageMaker, observability, with, Enhanced, Metrics</media:keywords>
</item>

<item>
<title>Reduce ASR inference costs by 75% with NVIDIA MPS on Amazon EC2</title>
<link>https://news.jatlink.uk/19750</link>
<guid>https://news.jatlink.uk/19750</guid>
<description><![CDATA[ Serving automatic speech recognition (ASR) models at scale is costly when each request uses only a fraction of a GPU. Learn how NVIDIA CUDA Multi-Process Service (MPS) with NVIDIA Triton Inference Server on Amazon EC2 GPU instances cuts GPU infrastructure by 75% while holding sub-second latency at 92.1 requests per second per GPU. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ML-21209-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 27 Aug 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reduce, ASR, inference, costs, 75, with, NVIDIA, MPS, Amazon, EC2</media:keywords>
</item>

<item>
<title>Evaluate any agent framework with Amazon Bedrock AgentCore Evaluations</title>
<link>https://news.jatlink.uk/19670</link>
<guid>https://news.jatlink.uk/19670</guid>
<description><![CDATA[ Amazon Bedrock AgentCore Evaluations decouples agent evaluation from the framework you build on. As long as your agent emits OpenTelemetry telemetry, the service can score it, whether you use LangGraph, LlamaIndex, the OpenAI Agents SDK, Google ADK, the Claude Agent SDK, or Strands Agents. This post explains how the framework-agnostic contract works. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/24/ML-21721-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 26 Aug 2026 22:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evaluate, any, agent, framework, with, Amazon, Bedrock, AgentCore, Evaluations</media:keywords>
</item>

<item>
<title>Bring your own model with Amazon SageMaker AI: Script mode in SDK v3</title>
<link>https://news.jatlink.uk/19652</link>
<guid>https://news.jatlink.uk/19652</guid>
<description><![CDATA[ The SageMaker Python SDK v3 redesigns script mode with unified ModelTrainer and ModelBuilder classes. This post walks through two end-to-end examples, a scikit-learn Random Forest and a multi-GPU Stable Diffusion 3.5 LoRA fine-tune, showing how SourceCode syncs your local code into any container at runtime so you can iterate without rebuilding Docker images. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/21/ML-21212-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 26 Aug 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Bring, your, own, model, with, Amazon, SageMaker, AI:, Script, mode, SDK</media:keywords>
</item>

<item>
<title>Preparing data for supervised fine&amp;tuning Part 2: Advanced data strategies</title>
<link>https://news.jatlink.uk/19653</link>
<guid>https://news.jatlink.uk/19653</guid>
<description><![CDATA[ The advanced side of supervised fine-tuning data prep. This second post in a two-part series covers evaluating data readiness with learning curves, selecting high-value data subsets, augmenting data with synthetic and distilled examples, and mixing data sources to prevent catastrophic forgetting. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/18/ML-20903P2-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 26 Aug 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Preparing, data, for, supervised, fine-tuning, Part, Advanced, data, strategies</media:keywords>
</item>

<item>
<title>Preparing data for supervised fine&amp;tuning Part 1: Formatting and quality</title>
<link>https://news.jatlink.uk/19654</link>
<guid>https://news.jatlink.uk/19654</guid>
<description><![CDATA[ Data preparation determines the ceiling of any supervised fine-tuning project. This first post in a two-part series covers the foundations of SFT data prep: quality checks, conversational (JSONL) formatting, reasoning and tool-calling schemas, and a representative train/evaluation split. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/18/ML-20903P1-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 26 Aug 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Preparing, data, for, supervised, fine-tuning, Part, Formatting, and, quality</media:keywords>
</item>

<item>
<title>Connect Amazon Bedrock AgentCore to cross&amp;account knowledge bases</title>
<link>https://news.jatlink.uk/19655</link>
<guid>https://news.jatlink.uk/19655</guid>
<description><![CDATA[ Learn how Amazon Bedrock AgentCore agents in one account can generate answers from an Amazon Bedrock knowledge base backed by Amazon Redshift Serverless in another account, without copying source data. This post covers the architecture, security boundary, and two orchestration models: a code-based Strands agent and a declarative AgentCore harness. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/21/ML-20558-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 26 Aug 2026 18:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Connect, Amazon, Bedrock, AgentCore, cross-account, knowledge, bases</media:keywords>
</item>

<item>
<title>How GoDaddy transformed its analytics with Amazon Quick</title>
<link>https://news.jatlink.uk/19650</link>
<guid>https://news.jatlink.uk/19650</guid>
<description><![CDATA[ In this post, you will learn how GoDaddy migrated from their legacy business intelligence (BI) tool to Amazon Quick. This was a two-year transformation that delivered results across every dimension of the business: 15,000 hours saved annually, 50% reduction in dashboard count, rendering times cut to under 5 seconds, and AI-powered self-service analytics now accessible to every employee. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/26/godaddy.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 26 Aug 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, GoDaddy, transformed, its, analytics, with, Amazon, Quick</media:keywords>
</item>

<item>
<title>Natera’s intelligent appointment scheduling with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/19651</link>
<guid>https://news.jatlink.uk/19651</guid>
<description><![CDATA[ Learn how Natera built an automated voice agent on Amazon Bedrock AgentCore that lets patients book mobile phlebotomy appointments through natural conversation. The post covers the dual-WebSocket bridge, event-driven latency masking, and progressive-trust authentication behind 100% tool-calling accuracy and sub-7-second latency. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/21/ML-20996-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 26 Aug 2026 18:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Natera’s, intelligent, appointment, scheduling, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Governed reports with Amazon Quick Desktop and Amazon FSx for NetApp ONTAP</title>
<link>https://news.jatlink.uk/19567</link>
<guid>https://news.jatlink.uk/19567</guid>
<description><![CDATA[ Build a governed weekly reporting workflow with Amazon Quick Desktop and Amazon FSx for NetApp ONTAP. An Amazon S3 access point exposes an approved folder to a Quick knowledge base, and a custom skill drafts cited weekly reports and Slack summaries with human review before anything is shared. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/18/ML-20626-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 25 Aug 2026 21:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Governed, reports, with, Amazon, Quick, Desktop, and, Amazon, FSx, for, NetApp, ONTAP</media:keywords>
</item>

<item>
<title>Agentic observability with Amazon OpenSearch Service MCP Apps</title>
<link>https://news.jatlink.uk/19566</link>
<guid>https://news.jatlink.uk/19566</guid>
<description><![CDATA[ Amazon OpenSearch Service now supports MCP Apps, which return interactive visualizations alongside your AI agent&#039;s text responses. Learn how a single, locally run MCP server lets your agent move from alert to trace to logs to root cause in one conversation, and how you can verify every step inline without leaving your IDE. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ML-21227-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 25 Aug 2026 21:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agentic, observability, with, Amazon, OpenSearch, Service, MCP, Apps</media:keywords>
</item>

<item>
<title>Building a restaurant telephony AI host with Amazon Connect</title>
<link>https://news.jatlink.uk/19480</link>
<guid>https://news.jatlink.uk/19480</guid>
<description><![CDATA[ Learn how to build a voice ordering system for restaurants that answers a phone call and takes an order end to end, with no app, no website, and no sign-in. It uses Amazon Connect for telephony, Amazon Connect Agentic Voice for real-time speech, an Amazon Connect AI agent for reasoning, and Amazon Bedrock AgentCore Gateway to reach backend tools through MCP. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/18/ML-21038-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 24 Aug 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, restaurant, telephony, host, with, Amazon, Connect</media:keywords>
</item>

<item>
<title>Agentic Resource Discovery (ARD): An open specification for agent discovery</title>
<link>https://news.jatlink.uk/19479</link>
<guid>https://news.jatlink.uk/19479</guid>
<description><![CDATA[ AWS Agent Registry gives your organization a centralized, searchable catalog for agents, tools, and skills. It works with the open Agentic Resource Discovery (ARD) standard to enable cross-environment discovery and governance at scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/20/ML-21618-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 24 Aug 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agentic, Resource, Discovery, ARD:, open, specification, for, agent, discovery</media:keywords>
</item>

<item>
<title>Introducing new Ray capabilities on SageMaker HyperPod</title>
<link>https://news.jatlink.uk/19477</link>
<guid>https://news.jatlink.uk/19477</guid>
<description><![CDATA[ Amazon SageMaker HyperPod now offers managed Ray support on Amazon EKS. Create and monitor Ray clusters, connect JupyterLab and Code Editor notebooks to live clusters, get out-of-the-box observability, and run resilient distributed training and accelerated inference from SageMaker Studio, all with open-source KubeRay and standard Ray APIs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/24/ML-21715-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 24 Aug 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, new, Ray, capabilities, SageMaker, HyperPod</media:keywords>
</item>

<item>
<title>Democratizing institutional knowledge: Building an AI&amp;powered knowledge management system with AWS</title>
<link>https://news.jatlink.uk/19478</link>
<guid>https://news.jatlink.uk/19478</guid>
<description><![CDATA[ Learn how to build a customizable, smart-caching knowledge management system on AWS that captures and delivers institutional (tribal) knowledge through a voice-first AI avatar. The accelerator uses Amazon Bedrock Knowledge Bases for retrieval-augmented generation and deploys in hours with AWS CloudFormation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/10/ML-18543-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 24 Aug 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Democratizing, institutional, knowledge:, Building, AI-powered, knowledge, management, system, with, AWS</media:keywords>
</item>

<item>
<title>AI&amp;powered metadata correction and harmonization</title>
<link>https://news.jatlink.uk/19455</link>
<guid>https://news.jatlink.uk/19455</guid>
<description><![CDATA[ Metadata harmonization (standardizing labels, identifiers, and formats so datasets can work together) is still largely manual. This post shows how AI-powered metadata correction works in practice, covering two approaches, human-in-the-loop validation and autonomous agent-driven workflows, plus governance considerations for production deployment. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20044/UI-Demo.mp4" length="49398" type="image/jpeg"/>
<pubDate>Mon, 24 Aug 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AI-powered, metadata, correction, and, harmonization</media:keywords>
</item>

<item>
<title>Agentic Data Operations Platform (ADOP): Data engineering into hours</title>
<link>https://news.jatlink.uk/19254</link>
<guid>https://news.jatlink.uk/19254</guid>
<description><![CDATA[ The Agentic Data Operations Platform (ADOP) is a reference architecture on Amazon Bedrock that uses specialized AI agents to automate the full Bronze-to-Silver-to-Gold data pipeline lifecycle, compressing new-source onboarding from weeks to hours while keeping data governance and compliance controls inline. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/18/ML-20916-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agentic, Data, Operations, Platform, ADOP:, Data, engineering, into, hours</media:keywords>
</item>

<item>
<title>Govern AI agent tool access with Amazon Bedrock AgentCore Gateway</title>
<link>https://news.jatlink.uk/19255</link>
<guid>https://news.jatlink.uk/19255</guid>
<description><![CDATA[ Give your AI agents governed, auditable access to enterprise tools without consolidating infrastructure. This post walks through a four-scope maturity model (Connect, Control, Catalog, and Harden) for building a governed tool gateway with Amazon Bedrock AgentCore, advancing only when real governance pain demands it. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ML-21003-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Govern, agent, tool, access, with, Amazon, Bedrock, AgentCore, Gateway</media:keywords>
</item>

<item>
<title>Reduce RAG costs on Amazon Bedrock with query&amp;aware compression</title>
<link>https://news.jatlink.uk/19256</link>
<guid>https://news.jatlink.uk/19256</guid>
<description><![CDATA[ Input tokens are often a meaningful part of the cost of running Retrieval Augmented Generation (RAG) at scale. This post describes a query-aware context compression pattern on Amazon Bedrock: after retrieval, a smaller model filters retrieved chunks against the query before the primary model answers, reducing input tokens and cost while preserving answer quality. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/19/ML-21148-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reduce, RAG, costs, Amazon, Bedrock, with, query-aware, compression</media:keywords>
</item>

<item>
<title>Accelerating aircraft IFEC diagnostics with agentic AI on AWS</title>
<link>https://news.jatlink.uk/19257</link>
<guid>https://news.jatlink.uk/19257</guid>
<description><![CDATA[ Panasonic Avionics worked with AWS and the AWS Generative AI Innovation Center to build an agentic AI system on Amazon Bedrock, Amazon SageMaker, and AWS Glue that diagnoses in-flight entertainment and connectivity (IFEC) issues across a global fleet, reducing diagnosis time from hours to minutes while maintaining accuracy. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/18/ML-20350-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerating, aircraft, IFEC, diagnostics, with, agentic, AWS</media:keywords>
</item>

<item>
<title>Build a no&amp;code ML workflow with Snowflake, Amazon SageMaker Canvas and Amazon Quick – Part 3: Visualizing insights with Amazon Quick Sight</title>
<link>https://news.jatlink.uk/19183</link>
<guid>https://news.jatlink.uk/19183</guid>
<description><![CDATA[ In Part 3 of this no-code ML series, you bring fraud detection predictions to life. Import your Amazon SageMaker Canvas predictions into Amazon Quick Sight, build interactive dashboards, use generative BI to answer questions in natural language, and publish AI-generated executive summaries for stakeholders. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/20/ml-20655-p3.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 01:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, no-code, workflow, with, Snowflake, Amazon, SageMaker, Canvas, and, Amazon, Quick, –, Part, Visualizing, insights, with, Amazon, Quick, Sight</media:keywords>
</item>

<item>
<title>Build a no&amp;code ML workflow with Snowflake, Amazon SageMaker Canvas and Amazon Quick – Part 1: Setting up your Snowflake environment</title>
<link>https://news.jatlink.uk/19181</link>
<guid>https://news.jatlink.uk/19181</guid>
<description><![CDATA[ Healthcare, retail, and life sciences teams store large volumes of operational data in Snowflake, but turning it into predictions is hard. In Part 1 of this series, you set up your AWS account and Snowflake environment for a no-code ML workflow with Amazon SageMaker Canvas, laying the foundation for building a fraud detection model without writing code. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ML-20655P1-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 01:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, no-code, workflow, with, Snowflake, Amazon, SageMaker, Canvas, and, Amazon, Quick, –, Part, Setting, your, Snowflake, environment</media:keywords>
</item>

<item>
<title>Build a no&amp;code ML workflow with Snowflake, Amazon SageMaker Canvas and Amazon Quick – Part 2: Data preparation and model building with Amazon SageMaker Canvas</title>
<link>https://news.jatlink.uk/19182</link>
<guid>https://news.jatlink.uk/19182</guid>
<description><![CDATA[ In Part 2 of this no-code ML series, you connect Amazon SageMaker Canvas to Snowflake, prepare and join transaction data with Data Wrangler visual transformations, and train an XGBoost fraud detection model. All without writing machine learning code, laying the groundwork for interactive dashboards in Part 3. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ML-20655P2-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 01:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, no-code, workflow, with, Snowflake, Amazon, SageMaker, Canvas, and, Amazon, Quick, –, Part, Data, preparation, and, model, building, with, Amazon, SageMaker, Canvas</media:keywords>
</item>

<item>
<title>Introducing cross&amp;Region inference for OpenAI GPT&amp;5.6 models on Amazon Bedrock</title>
<link>https://news.jatlink.uk/19180</link>
<guid>https://news.jatlink.uk/19180</guid>
<description><![CDATA[ Amazon Bedrock now offers OpenAI GPT-5.6 models (Sol, Terra, and Luna) in more than 25 AWS Regions with cross-Region inference. Learn how US geographic and global inference profiles route requests for higher throughput, how to call the models with the OpenAI and Converse APIs, and how to configure IAM, quotas, and monitoring. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/20/ml-21727.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 21 Aug 2026 01:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, cross-Region, inference, for, OpenAI, GPT-5.6, models, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>AWS vector solutions: Build agentic AI where your data lives</title>
<link>https://news.jatlink.uk/19162</link>
<guid>https://news.jatlink.uk/19162</guid>
<description><![CDATA[ AWS offers a broad portfolio of vector search built directly into the databases and storage services you already use, with no standalone vector database or data migration required. This post covers six purpose-built services, a decision framework for choosing the right engine, and customer proof points for each. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/18/ML-21681-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AWS, vector, solutions:, Build, agentic, where, your, data, lives</media:keywords>
</item>

<item>
<title>Authoring Dogwood policies from natural language in Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/19159</link>
<guid>https://news.jatlink.uk/19159</guid>
<description><![CDATA[ AI agents can take actions that do not match your organization&#039;s policies. Policy in Amazon Bedrock AgentCore lets teams enforce controls across agents, now including time-based constraints. This post shows how Policy Authoring turns natural-language policy documents into correct Dogwood policies, with worked examples and best practices. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/17/ML-21689-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 21:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Authoring, Dogwood, policies, from, natural, language, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Scaling agentic AI: Enterprise patterns without vendor lock&amp;in</title>
<link>https://news.jatlink.uk/19160</link>
<guid>https://news.jatlink.uk/19160</guid>
<description><![CDATA[ Scaling agentic AI across an enterprise requires patterns that preserve flexibility while avoiding vendor lock-in. In this second post of our multi-agent series, we examine how ML teams operate many agentic AI systems across a multi-everything environment of frameworks, models, and providers, and the principles that let those systems scale together. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ML-20861-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 21:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scaling, agentic, AI:, Enterprise, patterns, without, vendor, lock-in</media:keywords>
</item>

<item>
<title>Scaling cloud migrations with agentic AI on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/19161</link>
<guid>https://news.jatlink.uk/19161</guid>
<description><![CDATA[ Learn how AWS Professional Services uses a multi-agent framework built on Amazon Bedrock AgentCore to automate enterprise cloud migrations end to end. Purpose-built AI agents handle discovery, infrastructure as code generation, portfolio governance, and post-migration operations, reducing IaC development time from weeks to minutes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/12/ML-20875-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 21:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scaling, cloud, migrations, with, agentic, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Build intelligent security for healthcare APIs with Amazon Bedrock</title>
<link>https://news.jatlink.uk/19140</link>
<guid>https://news.jatlink.uk/19140</guid>
<description><![CDATA[ Learn how to add context-aware security monitoring to FHIR APIs using Amazon Bedrock. This post shows how to detect anomalous access patterns, classify data sensitivity automatically, and generate compliance reports in natural language, all without adding latency to clinical workflows. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/13/ML-19660-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, intelligent, security, for, healthcare, APIs, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>KnowledgeForge: mining gold from the ITSM ticket graveyard</title>
<link>https://news.jatlink.uk/19081</link>
<guid>https://news.jatlink.uk/19081</guid>
<description><![CDATA[ KnowledgeForge mines resolved ITSM incident tickets into new knowledge base articles and automatically curates the existing library by deduplicating, quality-scoring, and improving content, using Amazon Bedrock, Amazon S3 Vectors, and AWS Step Functions in a multi-tenant, closed-loop pipeline. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/13/ML-21271-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 01:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>KnowledgeForge:, mining, gold, from, the, ITSM, ticket, graveyard</media:keywords>
</item>

<item>
<title>Asynchronous patterns for calling Amazon Bedrock AgentCore agents in serverless pipelines</title>
<link>https://news.jatlink.uk/19079</link>
<guid>https://news.jatlink.uk/19079</guid>
<description><![CDATA[ In this post, you learn three serverless patterns (task-token callback, direct service integration, and durable functions) for invoking Amazon Bedrock AgentCore agents asynchronously from AWS Step Functions pipelines, eliminating idle compute costs while your AI agent processes requests. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ML-21461-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 01:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Asynchronous, patterns, for, calling, Amazon, Bedrock, AgentCore, agents, serverless, pipelines</media:keywords>
</item>

<item>
<title>How Fanatics Betting and Gaming built a multi&amp;agent customer support system</title>
<link>https://news.jatlink.uk/19080</link>
<guid>https://news.jatlink.uk/19080</guid>
<description><![CDATA[ Fanatics Betting and Gaming built a multi-agent customer support system on AWS to handle the complexity of sports betting: state-specific rules, real-time responsible gaming, and traffic spikes during major sporting events. This post walks through the architecture, the AWS services involved, and the patterns for your own multi-agent support solution. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/10/ML-20393-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 01:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Fanatics, Betting, and, Gaming, built, multi-agent, customer, support, system</media:keywords>
</item>

<item>
<title>Domain and publish date filters for Web Search on AgentCore</title>
<link>https://news.jatlink.uk/19077</link>
<guid>https://news.jatlink.uk/19077</guid>
<description><![CDATA[ Web Search on Amazon Bedrock AgentCore now supports runtime domain and published-date filtering. New per-request filters give developers per-call control over which web sources their agents consult and how fresh those sources must be, all enforced server-side. This release also expands Web Search to the Europe (Ireland) and Asia Pacific (Tokyo) Regions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/19/ML-21748-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 01:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Domain, and, publish, date, filters, for, Web, Search, AgentCore</media:keywords>
</item>

<item>
<title>Automate Document Processing with Quick Automate and the IDP Accelerator</title>
<link>https://news.jatlink.uk/19078</link>
<guid>https://news.jatlink.uk/19078</guid>
<description><![CDATA[ Classifying, extracting, and validating high volumes of documents is a challenge across banking, insurance, healthcare, and the public sector. See how a mid-size mortgage lender automates its entire document intake pipeline, from email to validated data, using the AWS GAIIC IDP Accelerator and Amazon Quick Automate. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ML-20366-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 20 Aug 2026 01:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, Document, Processing, with, Quick, Automate, and, the, IDP, Accelerator</media:keywords>
</item>

<item>
<title>How Axonius built secure multi&amp;tenant AI agents on Bedrock AgentCore</title>
<link>https://news.jatlink.uk/18973</link>
<guid>https://news.jatlink.uk/18973</guid>
<description><![CDATA[ Learn how Axonius, a cybersecurity SaaS provider, used Amazon Bedrock AgentCore to deploy fully isolated, multi-tenant AI agents across hundreds of customer environments, without building custom compute isolation, authentication, or observability infrastructure from scratch. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ML-21050-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 18 Aug 2026 21:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Axonius, built, secure, multi-tenant, agents, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Improve contract search accuracy with auto&amp;generated filters in Amazon Bedrock</title>
<link>https://news.jatlink.uk/18972</link>
<guid>https://news.jatlink.uk/18972</guid>
<description><![CDATA[ In this post, we describe how AIDA works at a high level and how it helps address these challenges — grounding users in the right contracts, under the right legal context, and within the right access boundaries. Specifically, we explore how AIDA uses implicit and explicit filtering, along with metadata-enriched chunking in Amazon Bedrock Knowledge Bases, to dramatically improve contract search accuracy. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/827bfc458708f0b442009c9c9836f7e4b65557fb/2020/06/03/Blog-Post_thumbnail.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 18 Aug 2026 21:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Improve, contract, search, accuracy, with, auto-generated, filters, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How Jumio built a real&amp;time feature store on AWS</title>
<link>https://news.jatlink.uk/18971</link>
<guid>https://news.jatlink.uk/18971</guid>
<description><![CDATA[ Learn how Jumio built a centralized, real-time feature store on AWS with Amazon SageMaker Feature Store, Amazon Managed Service for Apache Flink, and Amazon Kinesis Data Streams. The architecture delivers sub-100ms feature serving for fraud detection and saves approximately $120,000 annually. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/05/ML-19991-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 18 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Jumio, built, real-time, feature, store, AWS</media:keywords>
</item>

<item>
<title>Implement vector&amp;prompt document classification using Amazon Bedrock</title>
<link>https://news.jatlink.uk/18970</link>
<guid>https://news.jatlink.uk/18970</guid>
<description><![CDATA[ Learn how to build a multi-agent document classification solution on Amazon Bedrock using the Strands Agents SDK. Three specialized agents combine textual analysis with Claude Haiku 4.5 and visual similarity search with Amazon Titan Multimodal Embeddings to accurately classify insurance documents such as policies and affidavits. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/06/ML-18402-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 18 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implement, vector-prompt, document, classification, using, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Customize Amazon Quick embedded chat into your application</title>
<link>https://news.jatlink.uk/18969</link>
<guid>https://news.jatlink.uk/18969</guid>
<description><![CDATA[ Amazon Quick embedded chat brings a conversational AI interface into your web application. This post walks through customizing the embedded chat with container and SDK styling, branding removal, and a custom agent persona so it matches your brand&#039;s look, feel, and voice. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/13/ML-20497-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 18 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Customize, Amazon, Quick, embedded, chat, into, your, application</media:keywords>
</item>

<item>
<title>Amazon Bedrock AgentCore payments is now generally available: Enabling agents to transact safely and autonomously at scale</title>
<link>https://news.jatlink.uk/18968</link>
<guid>https://news.jatlink.uk/18968</guid>
<description><![CDATA[ Amazon Bedrock AgentCore payments is now generally available, enabling AI agents to autonomously transact at scale with built-in spending guardrails, protocol-agnostic payment orchestration, and production-ready observability. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21677/ACPaymentsQuickCreate3.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 18 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Bedrock, AgentCore, payments, now, generally, available:, Enabling, agents, transact, safely, and, autonomously, scale</media:keywords>
</item>

<item>
<title>NVIDIA Nemotron 3.5 Lightning now available in Amazon SageMaker JumpStart</title>
<link>https://news.jatlink.uk/18869</link>
<guid>https://news.jatlink.uk/18869</guid>
<description><![CDATA[ NVIDIA Nemotron 3.5 Lightning, an open model built for high-volume agentic workloads, is now available in Amazon SageMaker JumpStart. This post shows how to deploy the 30B Mixture-of-Experts model (3B active), which delivers up to 4x higher throughput and up to 30% faster task completion for always-on agents. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ML-21710-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 17 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>NVIDIA, Nemotron, 3.5, Lightning, now, available, Amazon, SageMaker, JumpStart</media:keywords>
</item>

<item>
<title>Build OpenClaw agents that transact with Amazon Bedrock AgentCore payments</title>
<link>https://news.jatlink.uk/18870</link>
<guid>https://news.jatlink.uk/18870</guid>
<description><![CDATA[ Give an autonomous agent a wallet and spending guardrails so it can pay for paywalled APIs, MCP servers, and web content. This post connects OpenClaw to Amazon Bedrock AgentCore payments and the x402 protocol, using the aws-agents-pay plugin to make bounded, human-approved testnet payments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-21616/ml-21616-Weather.mp4" length="49398" type="image/jpeg"/>
<pubDate>Mon, 17 Aug 2026 21:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, OpenClaw, agents, that, transact, with, Amazon, Bedrock, AgentCore, payments</media:keywords>
</item>

<item>
<title>Custom reward functions for multi&amp;turn reinforcement learning with Amazon Nova Forge</title>
<link>https://news.jatlink.uk/18650</link>
<guid>https://news.jatlink.uk/18650</guid>
<description><![CDATA[ In multi-turn reinforcement learning, your custom reward function decides what the model actually learns. This post shows how to design a composite multi-turn reward for Amazon Nova Forge, execute model-generated code safely inside it, and instrument each component to catch the pitfalls that quietly collapse a reward. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/14/ml-20735.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 14 Aug 2026 21:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Custom, reward, functions, for, multi-turn, reinforcement, learning, with, Amazon, Nova, Forge</media:keywords>
</item>

<item>
<title>Building agentic workflows with SageMaker AI and Bedrock AgentCore</title>
<link>https://news.jatlink.uk/18635</link>
<guid>https://news.jatlink.uk/18635</guid>
<description><![CDATA[ Learn how to combine OpenAI-compatible endpoints on Amazon SageMaker AI with Amazon Bedrock AgentCore runtime to build a multi-agent workflow where each specialized agent uses the model best suited to its job. This post also shows how to get token-level observability from SageMaker endpoints that Strands Agents does not instrument by default. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/10/ML-21454-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 14 Aug 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, agentic, workflows, with, SageMaker, and, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Monitor on&amp;premises and multi&amp;cloud AI agents with AgentCore Observability</title>
<link>https://news.jatlink.uk/18570</link>
<guid>https://news.jatlink.uk/18570</guid>
<description><![CDATA[ Set up Amazon Bedrock AgentCore Observability for AI agents running outside AWS: on-premises, on GCP, on Azure, or on developer machines. This walkthrough uses the AWS Distro for OpenTelemetry (ADOT) and IAM credentials to route session traces, span metrics, and token usage to the same AgentCore Observability dashboard. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/10/ML-20910-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 13 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Monitor, on-premises, and, multi-cloud, agents, with, AgentCore, Observability</media:keywords>
</item>

<item>
<title>Accelerating M&amp;amp;A due diligence with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/18546</link>
<guid>https://news.jatlink.uk/18546</guid>
<description><![CDATA[ Learn how to build a multi-agent M&amp;A due diligence system on Amazon Bedrock AgentCore. This post walks through a reference architecture that combines agent orchestration, knowledge retrieval, and governance controls, then deploys a complete sample you can run in your own AWS account. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/07/ML-19621-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 13 Aug 2026 17:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerating, M&amp;A, due, diligence, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Amazon Quick for Microsoft 365: Agentic AI where you work</title>
<link>https://news.jatlink.uk/18547</link>
<guid>https://news.jatlink.uk/18547</guid>
<description><![CDATA[ Amazon Quick is now available directly inside Microsoft Word, Excel, PowerPoint, and Outlook. These extensions bring connected data access and agentic document editing into the Microsoft 365 apps your teams already use, so you can analyze data, draft content, and reach enterprise knowledge without switching applications. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/ML-20556-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 13 Aug 2026 17:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Quick, for, Microsoft, 365:, Agentic, where, you, work</media:keywords>
</item>

<item>
<title>Automate legacy web applications with Amazon Bedrock AgentCore Browser Tool</title>
<link>https://news.jatlink.uk/18545</link>
<guid>https://news.jatlink.uk/18545</guid>
<description><![CDATA[ Learn how to automate legacy web applications that need human-like interaction using Amazon Bedrock AgentCore Browser Tool and Strands Agents. This walkthrough covers a reference architecture for an AI-powered digital worker that drives legacy interfaces through secure, isolated browser sessions while preserving human oversight and full audit trails. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ML-19368-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 13 Aug 2026 17:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, legacy, web, applications, with, Amazon, Bedrock, AgentCore, Browser, Tool</media:keywords>
</item>

<item>
<title>Part 2: Amazon Bedrock cost attribution with Amazon Athena and CUDOS</title>
<link>https://news.jatlink.uk/18467</link>
<guid>https://news.jatlink.uk/18467</guid>
<description><![CDATA[ Learn how to visualize and analyze Amazon Bedrock cost attribution using Amazon Athena and CUDOS dashboards. This post shows how to set up CUR 2.0 with IAM principal data, query Bedrock spend by principal, project, and team, and build dashboards to track AI costs across your organization. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/10/ML-21078-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 12 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Part, Amazon, Bedrock, cost, attribution, with, Amazon, Athena, and, CUDOS</media:keywords>
</item>

<item>
<title>Pay with confidence: How Solv Labs built verifiable, auditable agent payments on Amazon Bedrock AgentCore payments</title>
<link>https://news.jatlink.uk/18448</link>
<guid>https://news.jatlink.uk/18448</guid>
<description><![CDATA[ Solv Labs built a governed agent-payments workflow on Amazon Bedrock AgentCore payments, where every transaction is authorized, attested in an AWS Nitro Enclave, priced for risk, and anchored to a public blockchain before settlement. See how the pattern gives enterprises a verifiable, auditable trail for autonomous agent payments in regulated environments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/06/ML-21446-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 12 Aug 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Pay, with, confidence:, How, Solv, Labs, built, verifiable, auditable, agent, payments, Amazon, Bedrock, AgentCore, payments</media:keywords>
</item>

<item>
<title>Tiered KV cache for large LLMs on Amazon SageMaker HyperPod with Curvine</title>
<link>https://news.jatlink.uk/18449</link>
<guid>https://news.jatlink.uk/18449</guid>
<description><![CDATA[ Running large language model inference at scale forces a KV cache trade-off: oversized GPU instances or slow time-to-first-token. This post builds a tiered KV cache on Amazon SageMaker HyperPod that extends the cache into a shared, distributed NVMe pool with Curvine, so replicas reuse cache at near-local-disk speeds on cost-efficient instances. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/07/ML-21241-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 12 Aug 2026 17:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Tiered, cache, for, large, LLMs, Amazon, SageMaker, HyperPod, with, Curvine</media:keywords>
</item>

<item>
<title>How OneAdvanced deployed over 50 AI agents on UK&amp;sovereign AWS</title>
<link>https://news.jatlink.uk/18447</link>
<guid>https://news.jatlink.uk/18447</guid>
<description><![CDATA[ Learn how OneAdvanced, a UK enterprise software provider, built a UK-sovereign AI platform by self-hosting Llama 4 Maverick and Llama Guard 4 on Amazon SageMaker AI, with a RAG pipeline on pgvector and over 50 agents built with Strands Agents SDK on Amazon ECS. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/03/ML-20317-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 12 Aug 2026 17:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, OneAdvanced, deployed, over, agents, UK-sovereign, AWS</media:keywords>
</item>

<item>
<title>Accelerate cyber defense with OpenAI and AWS: Daybreak Red &amp;amp; Daybreak Blue now available to eligible customers on Amazon Bedrock</title>
<link>https://news.jatlink.uk/18377</link>
<guid>https://news.jatlink.uk/18377</guid>
<description><![CDATA[ Daybreak Red and Daybreak Blue from OpenAI, specialized cyber defense models from OpenAI, are now available on Amazon Bedrock to eligible customers. Both models run with zero-operator access enforced at the chip, keeping your code and vulnerability data secure. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/11/Screenshot-2026-08-11-at-4.37.01 PM-1130x630.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 12 Aug 2026 01:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerate, cyber, defense, with, OpenAI, and, AWS:, Daybreak, Red, Daybreak, Blue, now, available, eligible, customers, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How ONESTRUCTION built the Ishigaki&amp;IDS foundation model with AWS GenAIIC</title>
<link>https://news.jatlink.uk/18358</link>
<guid>https://news.jatlink.uk/18358</guid>
<description><![CDATA[ ONESTRUCTION, with technical advisory from the AWS Generative AI Innovation Center, built Ishigaki-IDS, a foundation model specialized for construction and BIM workflows. This architectural case study shows how they combined synthetic data, a three-stage training pipeline, and verifiable rewards on Amazon EC2 to build a domain model in a data-scarce field. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/05/ML-21069-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 11 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, ONESTRUCTION, built, the, Ishigaki-IDS, foundation, model, with, AWS, GenAIIC</media:keywords>
</item>

<item>
<title>How Pixieset achieved 35% AI feature adoption by solving the right problem with Amazon Bedrock</title>
<link>https://news.jatlink.uk/18359</link>
<guid>https://news.jatlink.uk/18359</guid>
<description><![CDATA[ Photographers are among the most skeptical audiences for generative AI. Learn how Pixieset used Amazon Bedrock to launch an AI-generated alt text feature to millions of users in four months, reaching 35% adoption by automating the tedious image SEO work photographers avoid, without touching the creative craft they take pride in. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/ML-18681-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 11 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Pixieset, achieved, 35, feature, adoption, solving, the, right, problem, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>First Orion accelerates QA automation using Amazon Nova Act</title>
<link>https://news.jatlink.uk/18360</link>
<guid>https://news.jatlink.uk/18360</guid>
<description><![CDATA[ Learn how First Orion, a branded communications company, shifted from brittle script-based UI testing to AI-driven QA automation with Amazon Nova Act. By describing tests in plain English instead of maintaining selector-based code, they cut QA cycle times, freed engineering capacity, and caught regressions earlier. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ML-20843-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 11 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>First, Orion, accelerates, automation, using, Amazon, Nova, Act</media:keywords>
</item>

<item>
<title>Deploying Anthropic Claude apps gateway for AWS for enterprise workloads</title>
<link>https://news.jatlink.uk/18338</link>
<guid>https://news.jatlink.uk/18338</guid>
<description><![CDATA[ Claude apps gateway is a self-hosted governance layer between Claude Code and Claude Desktop and Amazon Bedrock or Claude Platform on AWS. This post presents a production reference deployment covering end-to-end architecture, enterprise deployment patterns, cost, and implementation resources. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/06/ML-21574-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 11 Aug 2026 17:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploying, Anthropic, Claude, apps, gateway, for, AWS, for, enterprise, workloads</media:keywords>
</item>

<item>
<title>Run interactive IDEs on Amazon EKS with SageMaker AI to power up your AI workflows</title>
<link>https://news.jatlink.uk/18258</link>
<guid>https://news.jatlink.uk/18258</guid>
<description><![CDATA[ The Amazon SageMaker AI Spaces add-on for Amazon EKS runs managed JupyterLab and Code Editor environments on the cluster your ML team already operates. This post shows how to install and configure the add-on, connect from the browser and from VS Code over SSH-over-SSM, and move your team to OpenID Connect sign-in with Amazon Cognito. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/06/ML-20787-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 10 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Run, interactive, IDEs, Amazon, EKS, with, SageMaker, power, your, workflows</media:keywords>
</item>

<item>
<title>How nOps shipped FinOps agents 75% faster with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/18259</link>
<guid>https://news.jatlink.uk/18259</guid>
<description><![CDATA[ nOps rebuilt its Clara FinOps AI agent on Amazon Bedrock AgentCore, replacing a self-managed Amazon EKS stack running LangChain and LangGraph. The move cut time-to-production by 75% (from 10-12 months to 4 months), improved response quality, and reduced operational overhead while keeping analytics governed through Databricks Lakehouse Metric Views. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/ML-20862-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 10 Aug 2026 21:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, nOps, shipped, FinOps, agents, 75, faster, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Determining playoff clinching scenarios in the NHL using constraint programming</title>
<link>https://news.jatlink.uk/18021</link>
<guid>https://news.jatlink.uk/18021</guid>
<description><![CDATA[ The AWS Generative AI Innovation Center built an automated system that uses constraint programming and custom tree search to determine, with mathematical certainty, when and how an NHL team clinches a playoff spot. The approach was validated against four full NHL seasons of officially published results. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ML-21367-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 07 Aug 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Determining, playoff, clinching, scenarios, the, NHL, using, constraint, programming</media:keywords>
</item>

<item>
<title>How TReNDS automates root&amp;cause analysis with Amazon Bedrock</title>
<link>https://news.jatlink.uk/18020</link>
<guid>https://news.jatlink.uk/18020</guid>
<description><![CDATA[ TReNDS, a research center at Georgia State University, built an agentic AI pipeline on Amazon Bedrock and the open-source Strands Agents SDK that automatically investigates production errors in real time, reducing root-cause analysis from 15 to 30 minutes of manual work to under 60 seconds. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/07/ml-21106.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 07 Aug 2026 19:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, TReNDS, automates, root-cause, analysis, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/18019</link>
<guid>https://news.jatlink.uk/18019</guid>
<description><![CDATA[ In this post, you learn how Cohere Health built a multi-tenant agentic architecture on AgentCore using AgentCore Runtime’s secure MicroVM isolation, unified tool access through AgentCore Gateway, AgentCore Memory, and the Agent Skills open standard to rapidly scale policy digitization capabilities, while preserving transparency, version control, and human oversight. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/07/ml-19805.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 07 Aug 2026 19:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Cohere, Health, digitizes, clinical, policies, using, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Securing AI agents with temporal policies in Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/17936</link>
<guid>https://news.jatlink.uk/17936</guid>
<description><![CDATA[ Temporal policies in Amazon Bedrock AgentCore let you define stateful rules that evaluate authorization based on an agent&#039;s session history. Learn how to enforce workflow sequencing, prevent data fabrication, cap financial exposure, and require human approval for high-value actions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/06/ML-21661-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 23:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Securing, agents, with, temporal, policies, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>LLM optimization integration for Amazon SageMaker Python SDK</title>
<link>https://news.jatlink.uk/17918</link>
<guid>https://news.jatlink.uk/17918</guid>
<description><![CDATA[ The Amazon SageMaker Python SDK v3 now exposes generative AI inference recommendations in Amazon SageMaker AI directly in your notebook. Benchmark an endpoint, generate data-driven deployment recommendations, and deploy the recommended configuration without leaving your notebook workflow. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/05/ML-21556-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>LLM, optimization, integration, for, Amazon, SageMaker, Python, SDK</media:keywords>
</item>

<item>
<title>Building an agentic app deployer with Amazon Bedrock and AWS Lambda</title>
<link>https://news.jatlink.uk/17917</link>
<guid>https://news.jatlink.uk/17917</guid>
<description><![CDATA[ PDI Technologies built PDI Brew, an agentic platform on AWS where non-technical employees describe a tool in plain English and receive a fully provisioned, multi-tenant web application in seconds. See how a pluggable planner and an AWS Lambda provisioning agent turn plain-English intent into governed, multi-tenant apps backed by Amazon Bedrock. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/28/21066.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, agentic, app, deployer, with, Amazon, Bedrock, and, AWS, Lambda</media:keywords>
</item>

<item>
<title>Control agent behaviors and cost beyond a single action: new capabilities in Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/17913</link>
<guid>https://news.jatlink.uk/17913</guid>
<description><![CDATA[ Learn about new capabilities in Amazon Bedrock AgentCore: temporal policies powered by Dogwood, a new open source policy language for AI agents, and rate limiting on the gateway. These features give you deterministic control over sequences of agent actions and cost ceilings that hold regardless of agent behavior. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/05/ML-21657-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Control, agent, behaviors, and, cost, beyond, single, action:, new, capabilities, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Build visibility for Codex on Amazon Bedrock with OpenTelemetry and Amazon CloudWatch</title>
<link>https://news.jatlink.uk/17914</link>
<guid>https://news.jatlink.uk/17914</guid>
<description><![CDATA[ As engineering teams adopt coding agents like Codex, leaders need visibility into adoption, consumption, and reliability. This post shows how to route Codex OpenTelemetry metrics through a local collector to Amazon CloudWatch for an AWS native view of usage by user, team, and cost center. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/21583.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, visibility, for, Codex, Amazon, Bedrock, with, OpenTelemetry, and, Amazon, CloudWatch</media:keywords>
</item>

<item>
<title>Enforcing data residency with single&amp;Region Claude Code on Amazon Bedrock</title>
<link>https://news.jatlink.uk/17915</link>
<guid>https://news.jatlink.uk/17915</guid>
<description><![CDATA[ A regulated customer needed all Claude Code inference processed in a single AWS Region (London), not just in-geography. This post shows two ways to pin Claude Code on Amazon Bedrock to one Region: an application inference profile or the Mantle endpoint, paired with an IAM Region condition, plus how to verify compliance in AWS CloudTrail. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ML-21331-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Enforcing, data, residency, with, single-Region, Claude, Code, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Agent Skills for Automated Reasoning policies in Amazon Bedrock</title>
<link>https://news.jatlink.uk/17916</link>
<guid>https://news.jatlink.uk/17916</guid>
<description><![CDATA[ Learn how to run the full Amazon Bedrock Automated Reasoning policy lifecycle from your coding agent. A suite of open source Agent Skills builds, reviews, tests, debugs, deploys, and validates a custom policy end to end, turning a specialized console task into a repeatable engineering workflow. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/05/ML-21386-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agent, Skills, for, Automated, Reasoning, policies, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Configure rate limits for AI traffic on AgentCore gateway</title>
<link>https://news.jatlink.uk/17912</link>
<guid>https://news.jatlink.uk/17912</guid>
<description><![CDATA[ Learn how to configure rate limits on Amazon Bedrock AgentCore gateway to enforce per-user and per-target traffic controls. Define request, token, and connection limits scoped by JWT claims or IAM identity to protect downstream models, tools, and agents from traffic spikes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/06/ML-21567-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 06 Aug 2026 19:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Configure, rate, limits, for, traffic, AgentCore, gateway</media:keywords>
</item>

<item>
<title>Run production AI agents in n8n with Amazon Bedrock AgentCore harness</title>
<link>https://news.jatlink.uk/17819</link>
<guid>https://news.jatlink.uk/17819</guid>
<description><![CDATA[ Amazon Bedrock AgentCore harness is now generally available. Learn how to add it as an agent step in n8n workflows using a new open-source community node, and build agents with persistent memory, real tools, code execution, and VPC isolation — all from the n8n editor with no infrastructure or agent code. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/27/21089.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 05 Aug 2026 23:00:07 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Run, production, agents, n8n, with, Amazon, Bedrock, AgentCore, harness</media:keywords>
</item>

<item>
<title>How we built an MCP bridge to give our AgentCore&amp;hosted AI agent access to local MCP tools</title>
<link>https://news.jatlink.uk/17818</link>
<guid>https://news.jatlink.uk/17818</guid>
<description><![CDATA[ AI agents on Amazon Bedrock AgentCore run in the cloud, but users&#039; tools and files live on their laptops. Learn how to build a secure MCP bridge that lets a cloud-hosted agent call local MCP servers by tunneling signed messages over the existing WebSocket connection through a browser extension and Chrome native messaging, with no open ports or VPN required. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/28/21062.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 05 Aug 2026 23:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, built, MCP, bridge, give, our, AgentCore-hosted, agent, access, local, MCP, tools</media:keywords>
</item>

<item>
<title>How LendingTree built a multi&amp;agent mortgage assistant on Amazon Bedrock</title>
<link>https://news.jatlink.uk/17816</link>
<guid>https://news.jatlink.uk/17816</guid>
<description><![CDATA[ Learn how LendingTree built a production multi-agent mortgage assistant on Amazon Bedrock. Three coordinated agents use LangGraph, the Model Context Protocol, and Amazon Nova models with built-in guardrails to deliver 24/7 personalized mortgage guidance while meeting strict financial-services compliance. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/ML-21123-featured-image.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 05 Aug 2026 23:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, LendingTree, built, multi-agent, mortgage, assistant, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How Mobileye transformed support operations using Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/17817</link>
<guid>https://news.jatlink.uk/17817</guid>
<description><![CDATA[ In this post, we&#039;ll explore how Mobileye deployed an AI support agentic solution on Amazon Bedrock AgentCore - from the support bottleneck that sparked the idea, through the proof of concept that validated it, to the hybrid architecture that bridges on-premises systems with AWS cloud services. This approach is relevant for enterprises struggling to scale AI Agents while maintaining enterprise grade governance and security standards. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/20254.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 05 Aug 2026 23:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Mobileye, transformed, support, operations, using, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Introducing Web Search on Amazon Bedrock for foundation model grounding</title>
<link>https://news.jatlink.uk/17729</link>
<guid>https://news.jatlink.uk/17729</guid>
<description><![CDATA[ Today, we are introducing the general availability of Web Search on Amazon Bedrock. It is a server-side built-in tool that grounds model responses in current web knowledge. With Web Search, grounding becomes a native capability of Amazon Bedrock, with no third-party vendors to onboard, no external APIs to orchestrate, and no additional third party vendor security reviews to conduct. In this post, we walk through what Web Search on Amazon Bedrock is, why it matters, how to enable it using the OpenAI Responses API, and how to get started with the tool. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ml-21265.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 04 Aug 2026 23:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Web, Search, Amazon, Bedrock, for, foundation, model, grounding</media:keywords>
</item>

<item>
<title>Automated web insight extraction with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/17707</link>
<guid>https://news.jatlink.uk/17707</guid>
<description><![CDATA[ Extracting insights from dozens of websites by hand quickly becomes overwhelming. This post shows how to build an automated web insight extraction solution with Amazon Bedrock AgentCore Browser, Amazon Bedrock, Amazon OpenSearch Serverless, and AWS Lambda that monitors RSS feeds, renders pages reliably, and makes AI-extracted insights searchable. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/04/ml-20018.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 04 Aug 2026 19:00:04 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automated, web, insight, extraction, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Automated Reasoning policy refinement in Amazon Bedrock</title>
<link>https://news.jatlink.uk/17606</link>
<guid>https://news.jatlink.uk/17606</guid>
<description><![CDATA[ Amazon Bedrock now supports automatic Automated Reasoning policy refinement. The refinement engine diagnoses failing tests and proposes formal-logic fixes for rule issues and language issues, and you approve every change before it takes effect. This post walks through both refinement modes with complete API and console workflows. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/27/21259.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 03 Aug 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automated, Reasoning, policy, refinement, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>From weeks to minutes: How Formula 1® uses agentic AI on AWS to accelerate data operations</title>
<link>https://news.jatlink.uk/17605</link>
<guid>https://news.jatlink.uk/17605</guid>
<description><![CDATA[ Formula 1® partnered with AWS to build the Data Accelerator, using agentic AI on Amazon Bedrock AgentCore to transform its MarTech data platform. Learn how F1 cut data source onboarding from up to 8 weeks to about 40 minutes, automated schema evolution, and gained end-to-end observability across its fan-engagement data estate. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/08/03/ml-21186.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 03 Aug 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, weeks, minutes:, How, Formula, 1®, uses, agentic, AWS, accelerate, data, operations</media:keywords>
</item>

<item>
<title>Deploying Kimi K3 on Amazon SageMaker HyperPod and Amazon EKS</title>
<link>https://news.jatlink.uk/17395</link>
<guid>https://news.jatlink.uk/17395</guid>
<description><![CDATA[ This post walks through deploying Kimi K3 on AWS using two approaches: Amazon SageMaker HyperPod, and  Amazon Elastic Kubernetes Service (Amazon EKS) cluster. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/kimi-k3.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 31 Jul 2026 23:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploying, Kimi, Amazon, SageMaker, HyperPod, and, Amazon, EKS</media:keywords>
</item>

<item>
<title>Announcing the Agentic Catalog Experience in Amazon Quick</title>
<link>https://news.jatlink.uk/17394</link>
<guid>https://news.jatlink.uk/17394</guid>
<description><![CDATA[ Amazon Quick introduces the Agentic Catalog Experience, an AI-powered workflow for data curators to discover upstream catalog assets in natural language and auto-create Datasets and Topics with inherited semantics. Now in preview for AWS Glue Data Catalog and Databricks Unity Catalog. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/Announcing-the-Agentic-Catalog-Experience-in-Amazon-Quick.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 31 Jul 2026 23:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Announcing, the, Agentic, Catalog, Experience, Amazon, Quick</media:keywords>
</item>

<item>
<title>Optimizing production agents with Amazon Bedrock AgentCore Observability</title>
<link>https://news.jatlink.uk/17382</link>
<guid>https://news.jatlink.uk/17382</guid>
<description><![CDATA[ As your AI agents move from prototype to production, the challenge shifts from getting them to work to keeping them fast and efficient. Learn how to use Amazon Bedrock AgentCore Observability and Amazon CloudWatch to find performance bottlenecks and diagnose memory issues in long-running agent sessions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/31/ml-20467.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 31 Jul 2026 19:00:04 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Optimizing, production, agents, with, Amazon, Bedrock, AgentCore, Observability</media:keywords>
</item>

<item>
<title>Migrate your prompts to new models and optimize them on Amazon Bedrock</title>
<link>https://news.jatlink.uk/17283</link>
<guid>https://news.jatlink.uk/17283</guid>
<description><![CDATA[ Amazon Bedrock Advanced Prompt Optimization optimizes your prompts for up to 5 models at once and compares original versus optimized performance across quality, latency, and cost. Migrate to a new model or improve your current one in minutes instead of weeks. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/28/20950.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Jul 2026 19:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Migrate, your, prompts, new, models, and, optimize, them, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>How Yahoo enhances search retargeting using Amazon Bedrock</title>
<link>https://news.jatlink.uk/17280</link>
<guid>https://news.jatlink.uk/17280</guid>
<description><![CDATA[ In this post, we demonstrate how Yahoo implemented Amazon Bedrock to enhance their Search Retargeting (SRT) capabilities in the Yahoo DSP ad tech suite. SRT is a core audience targeting solution that helps advertisers reach users based on their historical search behavior, bridging search intent with display, video, and native advertising. Beyond targeting keywords entered on Yahoo Search, SRT uses AI to identify and engage users who demonstrate intent through search activity both on Yahoo and across integrated partner systems. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/30/ML-18912.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Yahoo, enhances, search, retargeting, using, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Inference meta&amp;monitoring for Amazon SageMaker AI endpoints with Amazon Quick</title>
<link>https://news.jatlink.uk/17281</link>
<guid>https://news.jatlink.uk/17281</guid>
<description><![CDATA[ Learn how to build an inference meta-monitoring system for Amazon SageMaker AI endpoints using Amazon Quick. This governance layer sits above production ML inference pipelines to continuously track prediction and data quality, detect drift, integrate delayed ground truth, and surface automated performance dashboards. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/28/20850.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Inference, meta-monitoring, for, Amazon, SageMaker, endpoints, with, Amazon, Quick</media:keywords>
</item>

<item>
<title>Introducing explicit prompt caching for OpenAI GPT&amp;5.6 models on Amazon Bedrock</title>
<link>https://news.jatlink.uk/17282</link>
<guid>https://news.jatlink.uk/17282</guid>
<description><![CDATA[ OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock, along with explicit prompt caching that gives you precise control over which parts of your prompt are cached and reused. Learn how to get started, set up explicit caching, and migrate existing GPT workloads to reduce inference cost. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/30/ml-21452.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, explicit, prompt, caching, for, OpenAI, GPT-5.6, models, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Deploying Kimi K3 on AWS</title>
<link>https://news.jatlink.uk/17279</link>
<guid>https://news.jatlink.uk/17279</guid>
<description><![CDATA[ This post walks through deploying Kimi K3 on AWS using two approaches: Amazon SageMaker HyperPod, and  Amazon Elastic Kubernetes Service (Amazon EKS) cluster. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/30/ml-21615.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Jul 2026 19:00:04 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploying, Kimi, AWS</media:keywords>
</item>

<item>
<title>Automating customer retention workflows in Amazon Quick</title>
<link>https://news.jatlink.uk/17181</link>
<guid>https://news.jatlink.uk/17181</guid>
<description><![CDATA[ Learn how to build a no-code customer retention pipeline in Amazon Quick that detects at-risk customers from call transcripts and CSAT data, scores them by retention priority with a custom MCP Action, and generates personalized retention letters, reducing response time from days to minutes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/23/21125.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 29 Jul 2026 19:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automating, customer, retention, workflows, Amazon, Quick</media:keywords>
</item>

<item>
<title>Authenticate with Private Key JWT using Amazon Bedrock AgentCore Identity</title>
<link>https://news.jatlink.uk/17179</link>
<guid>https://news.jatlink.uk/17179</guid>
<description><![CDATA[ This post explains how Private Key JWT client authentication works in AgentCore Identity and reviews the supported grant flows. We then walk through creating an AWS KMS signing key, registering its public key with your identity provider, configuring a credential provider on the AWS Management Console, and reviewing example AWS CloudTrail events that record your agent’s access. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/29/ml-21480.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 29 Jul 2026 19:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Authenticate, with, Private, Key, JWT, using, Amazon, Bedrock, AgentCore, Identity</media:keywords>
</item>

<item>
<title>Generate Autonomous Business Insights with AI Agent and MCP Servers</title>
<link>https://news.jatlink.uk/17180</link>
<guid>https://news.jatlink.uk/17180</guid>
<description><![CDATA[ Learn how Amazon Bedrock AgentCore delivers autonomous, cross-system business intelligence through configuration rather than custom code. Using pre-built MCP server connectors, fine-grained access control, and persistent memory, enterprises can query multiple data sources with natural language while enforcing role-based boundaries automatically. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/29/ml-19801.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 29 Jul 2026 19:00:06 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Generate, Autonomous, Business, Insights, with, Agent, and, MCP, Servers</media:keywords>
</item>

<item>
<title>How AgentCore Gateway supports the MCP 2026&amp;07&amp;28 spec</title>
<link>https://news.jatlink.uk/17103</link>
<guid>https://news.jatlink.uk/17103</guid>
<description><![CDATA[ The Model Context Protocol (MCP) published its 2026-07-28 specification, the largest revision since launch: MCP is now stateless, with a governed extensions system and hardened authorization. Learn what changed and how to enable the new version on Amazon Bedrock AgentCore Gateway with a single UpdateGateway call. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/28/21559.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 28 Jul 2026 23:00:04 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, AgentCore, Gateway, supports, the, MCP, 2026-07-28, spec</media:keywords>
</item>

<item>
<title>Market surveillance agent with LangGraph and Strands on AgentCore</title>
<link>https://news.jatlink.uk/17085</link>
<guid>https://news.jatlink.uk/17085</guid>
<description><![CDATA[ Learn how to architect and deploy a production-ready multi-agent AI system using LangGraph for workflow orchestration and Strands for agent reasoning on Amazon Bedrock AgentCore. This post walks through a market surveillance example with state-driven orchestration, checkpoint-based recovery, and AgentCore memory and observability. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/24/19945.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 28 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Market, surveillance, agent, with, LangGraph, and, Strands, AgentCore</media:keywords>
</item>

<item>
<title>How Guardoc transforms medical document processing with Amazon Nova models</title>
<link>https://news.jatlink.uk/16998</link>
<guid>https://news.jatlink.uk/16998</guid>
<description><![CDATA[ In this post, we explore how Guardoc Health uses the Amazon Nova family of models, available through Amazon Bedrock, to transform clinical documentation in long-term care. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/27/ml-20888.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 27 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Guardoc, transforms, medical, document, processing, with, Amazon, Nova, models</media:keywords>
</item>

<item>
<title>Beyond RAG: Task&amp;aware knowledge compression for enterprise AI on AWS</title>
<link>https://news.jatlink.uk/16996</link>
<guid>https://news.jatlink.uk/16996</guid>
<description><![CDATA[ Traditional RAG hits a ceiling on analytical tasks that span hundreds of documents. This post shows how to use task-aware knowledge compression (TAKC) on AWS to pre-compress entire knowledge bases into task-specific representations, cache them at multiple fidelity tiers, and route each query to the right tier, with an open-source implementation you can deploy. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/23/19433.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 27 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Beyond, RAG:, Task-aware, knowledge, compression, for, enterprise, AWS</media:keywords>
</item>

<item>
<title>Deepgram enhances Amazon SageMaker AI support with AWS IAM Temporary Delegation</title>
<link>https://news.jatlink.uk/16997</link>
<guid>https://news.jatlink.uk/16997</guid>
<description><![CDATA[ In this post, we cover why Deepgram built on IAM temporary delegation, how the integration works end-to-end, and what it unlocks for customers running Deepgram speech models on SageMaker AI. With this integration, Deepgram has reduced the time for initial investigation on a SageMaker AI support ticket from days to minutes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/27/ml-21067.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 27 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deepgram, enhances, Amazon, SageMaker, support, with, AWS, IAM, Temporary, Delegation</media:keywords>
</item>

<item>
<title>Get started with OpenAI GPT&amp;5.6 Sol, Terra, and Luna on Amazon Bedrock</title>
<link>https://news.jatlink.uk/16789</link>
<guid>https://news.jatlink.uk/16789</guid>
<description><![CDATA[ OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock. Learn how to select a model, run inference through the Responses API on the bedrock-mantle endpoint, reduce cost with prompt caching, connect the OpenAI Codex coding agent, and plan for quotas and scaling. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/22/21450-1.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 24 Jul 2026 19:00:05 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Get, started, with, OpenAI, GPT-5.6, Sol, Terra, and, Luna, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Introducing Claude Opus 5 on AWS: Anthropic’s most capable Opus model</title>
<link>https://news.jatlink.uk/16787</link>
<guid>https://news.jatlink.uk/16787</guid>
<description><![CDATA[ This post covers Opus 5’s improvements and practical guidance for AI engineers integrating the model into agentic systems and production inference workloads on Amazon Bedrock. See the documentation for Claude Platform on AWS. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/24/ml-21458.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 24 Jul 2026 19:00:04 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Claude, Opus, AWS:, Anthropic’s, most, capable, Opus, model</media:keywords>
</item>

<item>
<title>Build an explainable next&amp;best&amp;product recommendation system for banking on AWS</title>
<link>https://news.jatlink.uk/16788</link>
<guid>https://news.jatlink.uk/16788</guid>
<description><![CDATA[ Learn the architecture and design decisions behind an explainable next-best-product recommendation system for banking, built with Amazon SageMaker AI and PyTorch. A multi-tower neural network with learned attention delivers accurate, per-customer recommendations while providing the explainability that banking regulators require. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/22/19387.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 24 Jul 2026 19:00:04 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, explainable, next-best-product, recommendation, system, for, banking, AWS</media:keywords>
</item>

<item>
<title>Best practices for applying Amazon Bedrock Guardrails to code generation workflows</title>
<link>https://news.jatlink.uk/16722</link>
<guid>https://news.jatlink.uk/16722</guid>
<description><![CDATA[ In this post, we explain how Amazon Bedrock Guardrails can be configured for code generation workflows with coding assistants to overcome these constraints. With these best practices, you can build an efficient blueprint helping you with effective capacity planning with robust safety coverage. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/22/21149.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 24 Jul 2026 03:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Best, practices, for, applying, Amazon, Bedrock, Guardrails, code, generation, workflows</media:keywords>
</item>

<item>
<title>Agentic retrieval for Amazon Bedrock Managed Knowledge Base</title>
<link>https://news.jatlink.uk/16692</link>
<guid>https://news.jatlink.uk/16692</guid>
<description><![CDATA[ This post focuses on why classic retrieval falls short on multi-part questions, how the AgenticRetrieveStream API works (including request construction and trace parsing), and when to choose it over the standard Retrieve API. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/23/ml-21281.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Jul 2026 19:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agentic, retrieval, for, Amazon, Bedrock, Managed, Knowledge, Base</media:keywords>
</item>

<item>
<title>Building multi&amp;Region visualizations with Highcharts in Amazon Quick</title>
<link>https://news.jatlink.uk/16690</link>
<guid>https://news.jatlink.uk/16690</guid>
<description><![CDATA[ This post shows you how to build multi-Region carrier performance dashboards in Quick Sight using Highcharts custom visualizations to overcome native chart limitations. You will learn how to maintain data sovereignty across AWS Regions while creating unified visualizations through the Quick Sight federated dataset capability. The solution includes production-ready chart configurations and addresses security, compliance, and scalability requirements. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/23/ml-21423.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Jul 2026 19:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, multi-Region, visualizations, with, Highcharts, Amazon, Quick</media:keywords>
</item>

<item>
<title>Detecting silent agent failures with Amazon Bedrock AgentCore optimization</title>
<link>https://news.jatlink.uk/16691</link>
<guid>https://news.jatlink.uk/16691</guid>
<description><![CDATA[ Amazon Bedrock AgentCore optimization surfaces silent behavioral failures in production AI agents: the ones that pass every health check but still deliver wrong outcomes. Learn how insights discovers, explains, and ranks failure patterns across sessions so you can fix the highest-impact issues first. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/22/21350.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Jul 2026 19:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Detecting, silent, agent, failures, with, Amazon, Bedrock, AgentCore, optimization</media:keywords>
</item>

<item>
<title>Evaluating AI Agents: A production blueprint with Strands and AgentCore</title>
<link>https://news.jatlink.uk/16688</link>
<guid>https://news.jatlink.uk/16688</guid>
<description><![CDATA[ Together, Motorway and AWS built an end-to-end evaluation pipeline that reduced incorrect results from 1 in 8 queries to 1 in 50 and cut issue detection time from few hours to few minutes. The pipeline combines the Strands Agents SDK with Amazon Bedrock AgentCore, a fully managed service for deploying and operating AI agents at scale. In this post, you will learn how to build this pipeline for your own agents. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/23/ml-20515.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evaluating, Agents:, production, blueprint, with, Strands, and, AgentCore</media:keywords>
</item>

<item>
<title>Building trade assistant: How Jefferies optimized front office trading operations with AI</title>
<link>https://news.jatlink.uk/16689</link>
<guid>https://news.jatlink.uk/16689</guid>
<description><![CDATA[ In this post, we explore how Jefferies overcame these challenges with a solution built on Strands Agents, an agent harness SDK for building AI agents that can reason, plan, and act by orchestrating calls to foundation models (FMs) and external tools. The solution uses large language models (LLMs), Amazon Bedrock, and Amazon Bedrock Knowledge Bases. It also uses Model Context Protocol (MCP), an open standard that helps AI agents securely connect to diverse data sources and tools through a unified interface. We cover the solution overview, the rationale for selecting the underlying technology stack, lessons learned, and the business impact the solution created at Jefferies. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/23/ml-20564.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, trade, assistant:, How, Jefferies, optimized, front, office, trading, operations, with</media:keywords>
</item>

<item>
<title>Build specialized agent workflows for your business with Amazon Quick and NVIDIA NeMo Relay</title>
<link>https://news.jatlink.uk/16626</link>
<guid>https://news.jatlink.uk/16626</guid>
<description><![CDATA[ In this post, we show how Amazon Quick can serve as the business-user front door for specialized agent workflows. We use the NVIDIA NeMo Relay to build a supply-chain risk example that helps a planner move from an Amazon Quick dashboard and knowledge context to a guided mitigation recommendation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/23/Build-specialized-agent-workflows-for-your-business-with-Amazon-Quick-and-NVIDIA-NeMo-Relay.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Jul 2026 03:00:16 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, specialized, agent, workflows, for, your, business, with, Amazon, Quick, and, NVIDIA, NeMo, Relay</media:keywords>
</item>

<item>
<title>AI Teammates: how monday.com runs production AI agents on Amazon Bedrock</title>
<link>https://news.jatlink.uk/16594</link>
<guid>https://news.jatlink.uk/16594</guid>
<description><![CDATA[ AI Teammates are agentic AI on Amazon Bedrock, and few engineering organizations run them in production at the scale that monday.com does. Nine in ten Builders use AI coding tools every month, up from roughly half a year ago. Per-engineer PR throughput is up by more than half. Every figure in this post comes from monday’s own internal production data. In this post, we share the architecture behind those numbers, the retrofits that made it work in a decade-old code base, and the confidence-scored merge play closing the gap to full autonomy. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/22/ML-21226.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 22 Jul 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Teammates:, how, monday.com, runs, production, agents, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Exploring self&amp;distilled reasoning for supervised fine&amp;tuning with Amazon Nova</title>
<link>https://news.jatlink.uk/16489</link>
<guid>https://news.jatlink.uk/16489</guid>
<description><![CDATA[ In this post, we explore an idea for generating thinking tokens for datasets that lack reasoning traces in SFT customization. We first examine the reasoning suppression problem, then introduce Self-Distilled Reasoning (SDR), validate it across three benchmarks, and provide practical recommendations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/21/ml-20897.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 21 Jul 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Exploring, self-distilled, reasoning, for, supervised, fine-tuning, with, Amazon, Nova</media:keywords>
</item>

<item>
<title>How Couchbase built a multi&amp;model AI architecture for Capella iQ with Amazon Bedrock</title>
<link>https://news.jatlink.uk/16399</link>
<guid>https://news.jatlink.uk/16399</guid>
<description><![CDATA[ This post describes how Couchbase adopted Amazon Bedrock to power Capella iQ with Anthropic’s Claude family of models, the architectural decisions behind their multi-model approach, and the operational benefits realized in production. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/20/ml-21175.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 20 Jul 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Couchbase, built, multi-model, architecture, for, Capella, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Evolving from legacy BI to agentic AI at Tradeshift with Amazon Quick</title>
<link>https://news.jatlink.uk/16400</link>
<guid>https://news.jatlink.uk/16400</guid>
<description><![CDATA[ In this post, we describe how Tradeshift deployed Amazon Quick with agentic AI capabilities to replace our legacy BI tool, resulting in query response times up to 30 times faster, a 40 percent reduction in total cost of ownership, and turned embedded analytics into a product that generates revenue. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21151/ML-21151-video1.mp4" length="49398" type="image/jpeg"/>
<pubDate>Mon, 20 Jul 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evolving, from, legacy, agentic, Tradeshift, with, Amazon, Quick</media:keywords>
</item>

<item>
<title>Custom OS installation now available on AWS DeepRacer devices</title>
<link>https://news.jatlink.uk/16397</link>
<guid>https://news.jatlink.uk/16397</guid>
<description><![CDATA[ With the stock firmware and software, developers couldn&#039;t modify their AWS DeepRacer devices to use the latest operating systems. Now, developers can upgrade or install a custom operating system (OS) by using a newly released bootloader, which extends the life of these hardware devices. In this post, we introduce the bootloader, discuss how to use it, and share links to a community distribution that uses it. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/20/ML-20957.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 20 Jul 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Custom, installation, now, available, AWS, DeepRacer, devices</media:keywords>
</item>

<item>
<title>Build specialized agent workflows for your business with Amazon Quick and NVIDIA NeMo Agent Toolkit</title>
<link>https://news.jatlink.uk/16398</link>
<guid>https://news.jatlink.uk/16398</guid>
<description><![CDATA[ In this post, we show how Amazon Quick can serve as the business-user front door for specialized agent workflows. We use the NVIDIA NeMo Agent Toolkit to build a supply-chain risk example that helps a planner move from an Amazon Quick dashboard and knowledge context to a guided mitigation recommendation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/20/ml-21387.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 20 Jul 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, specialized, agent, workflows, for, your, business, with, Amazon, Quick, and, NVIDIA, NeMo, Agent, Toolkit</media:keywords>
</item>

<item>
<title>Transform your sales organization with Amazon Quick: your new agentic AI teammate</title>
<link>https://news.jatlink.uk/16200</link>
<guid>https://news.jatlink.uk/16200</guid>
<description><![CDATA[ In this post, we walk through a few ways that Quick delivers on this promise. We cover the entire sales cycle, from identifying your highest-priority prospect, contacting them, working the deal to close, and keeping the CRM up to date as the account matures, while protecting your scarcest resource: your time. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/17/ml-20807-1.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 17 Jul 2026 23:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Transform, your, sales, organization, with, Amazon, Quick:, your, new, agentic, teammate</media:keywords>
</item>

<item>
<title>How Smartsheet built a remote MCP server on AWS</title>
<link>https://news.jatlink.uk/16180</link>
<guid>https://news.jatlink.uk/16180</guid>
<description><![CDATA[ In this post, we cover a high-level view of the Smartsheet remote MCP architecture, with a focus on the AWS infrastructure behind it. This includes security, governance, scaling and deployment, and the AI-specific optimizations Smartsheet built on AWS. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/17/ml-21139.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 17 Jul 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Smartsheet, built, remote, MCP, server, AWS</media:keywords>
</item>

<item>
<title>Introducing Mobile Layout for Amazon Quick dashboards</title>
<link>https://news.jatlink.uk/16179</link>
<guid>https://news.jatlink.uk/16179</guid>
<description><![CDATA[ Teams that rely on dashboards for daily decisions often must pinch and zoom to interact with controls originally designed for larger displays. Checking revenue during a morning standup, reviewing pipeline metrics between meetings, or monitoring operations while traveling all require extra effort when the dashboard was built for a desktop screen. Mobile Layout for Amazon […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/17/ml-20807.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 17 Jul 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Mobile, Layout, for, Amazon, Quick, dashboards</media:keywords>
</item>

<item>
<title>Introducing Grok on Amazon Bedrock</title>
<link>https://news.jatlink.uk/16109</link>
<guid>https://news.jatlink.uk/16109</guid>
<description><![CDATA[ This post covers what makes Grok 4.3 a great fit for agentic and enterprise workloads, how you access it through Amazon Bedrock, and how to use the capabilities most teams reach for first: a basic chat request, configurable reasoning effort, tool calling, structured output, image input, and stateful multi-turn conversations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/30/21284.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 16 Jul 2026 23:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Grok, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Build enterprise search for agents with Amazon Bedrock Managed Knowledge Base</title>
<link>https://news.jatlink.uk/16108</link>
<guid>https://news.jatlink.uk/16108</guid>
<description><![CDATA[ In this post, we walk through the three pillars that make this possible: simplified setup, smarter retrieval, and production readiness. We also show you code examples for setting up a knowledge base and retrieving from it. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/16/ml-20588.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 16 Jul 2026 23:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, enterprise, search, for, agents, with, Amazon, Bedrock, Managed, Knowledge, Base</media:keywords>
</item>

<item>
<title>Building a restaurant telephony AI host with Amazon Bedrock AgentCore and Amazon Nova 2 Sonic</title>
<link>https://news.jatlink.uk/16093</link>
<guid>https://news.jatlink.uk/16093</guid>
<description><![CDATA[ In this post, we show you how to build a voice ordering system that answers a phone number and takes the order from greeting to confirmation. The system uses Amazon Bedrock AgentCore to host and run the agent and Amazon Nova 2 Sonic for real-time speech, connected to a restaurant backend through the Model Context Protocol (MCP). The walkthrough covers deploying the full stack with AWS Cloud Development Kit (AWS CDK) and bridging a phone call into the agent through a Session Initiation Protocol (SIP) gateway on Amazon Elastic Container Service (Amazon ECS) and AWS Fargate. It also warms the agent session while the phone is still ringing, so the caller never hears dead air. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-21038/Recording-Audio-Normalied.mp4" length="49398" type="image/jpeg"/>
<pubDate>Thu, 16 Jul 2026 19:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, restaurant, telephony, host, with, Amazon, Bedrock, AgentCore, and, Amazon, Nova, Sonic</media:keywords>
</item>

<item>
<title>Monitor Amazon SageMaker Pipelines cross&amp;account with custom Amazon CloudWatch dashboards</title>
<link>https://news.jatlink.uk/16006</link>
<guid>https://news.jatlink.uk/16006</guid>
<description><![CDATA[ In this post, we present a solution designed to centralize the monitoring of SageMaker Pipelines across AWS accounts and Regions using Amazon CloudWatch custom dashboards. The accompanying GitHub repository provides a customizable AWS Cloud Development Kit (AWS CDK) example of the required infrastructure. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/15/ml-19114.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 15 Jul 2026 23:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Monitor, Amazon, SageMaker, Pipelines, cross-account, with, custom, Amazon, CloudWatch, dashboards</media:keywords>
</item>

<item>
<title>Built Technologies builds an AI&amp;powered document intelligence solution on AWS to power agents across real estate finance</title>
<link>https://news.jatlink.uk/16004</link>
<guid>https://news.jatlink.uk/16004</guid>
<description><![CDATA[ Built partnered with the AWS Generative AI Innovation Center (GenAIIC), AWS Partner AND Digital, and AWS account teams to create a scalable, AI-powered document processing engine that can classify, split, extract, evaluate, and reason over complex real estate finance documents. It reduces workflows that previously took days to minutes, supports hundreds of document types, and gives technical teams and industry experts a shared environment for building and improving document processors. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/15/ml-21017.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 15 Jul 2026 23:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Built, Technologies, builds, AI-powered, document, intelligence, solution, AWS, power, agents, across, real, estate, finance</media:keywords>
</item>

<item>
<title>Agentic vision: Building visual intelligence with Amazon Bedrock and MCP servers</title>
<link>https://news.jatlink.uk/16005</link>
<guid>https://news.jatlink.uk/16005</guid>
<description><![CDATA[ In this post, we walk you through the Computer Vision MCP Server, which illustrates this approach, representing how AI systems can process visual information and make intelligent decisions through a single, standardized interface. This convergence transforms what was once a complex integration challenge into a streamlined process, making AI capabilities accessible to a broader range of applications and developers. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/15/ml-18924.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 15 Jul 2026 23:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agentic, vision:, Building, visual, intelligence, with, Amazon, Bedrock, and, MCP, servers</media:keywords>
</item>

<item>
<title>Multi&amp;agent social intelligence with Strands Agents and Amazon Bedrock</title>
<link>https://news.jatlink.uk/15912</link>
<guid>https://news.jatlink.uk/15912</guid>
<description><![CDATA[ This post shows how Thrad.ai deployed a multi-agent system with Strands Agents and Amazon Bedrock AgentCore that automates the pipeline from prospect discovery through personalized email generation. The post compares two orchestration patterns (Swarm and Graph) with head-to-head benchmarks on latency, cost, and email quality. You’ll also learn how the system scores prospects using weighted criteria, intent classification, and temporal decay, plus governance controls for production deployment. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/24/19617.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 14 Jul 2026 23:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Multi-agent, social, intelligence, with, Strands, Agents, and, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>ScienceSoft’s HIPAA&amp;compliant AI voice scheduler built on AWS</title>
<link>https://news.jatlink.uk/15897</link>
<guid>https://news.jatlink.uk/15897</guid>
<description><![CDATA[ In this post, you will learn how ScienceSoft, an Amazon Web Services (AWS) Services Partner, integrated Amazon Nova 2 Sonic with Amazon Bedrock Guardrails to build a Health Insurance Portability and Accountability Act (HIPAA)-compliant AI voice scheduler. You will see how the solution addresses healthcare scheduling challenges while maintaining privacy, compliance, and responsible AI standards, and how you can apply the same architecture to your own workflows. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/14/ml-19470.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 14 Jul 2026 19:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>ScienceSoft’s, HIPAA-compliant, voice, scheduler, built, AWS</media:keywords>
</item>

<item>
<title>Scaling medical content review at Flo Health with Amazon Bedrock – Part 2</title>
<link>https://news.jatlink.uk/15896</link>
<guid>https://news.jatlink.uk/15896</guid>
<description><![CDATA[ In this post, we share how Flo Health’s engineering team turned a proof of concept (PoC) from the AWS Generative AI Innovation Center into a production-grade, AI-powered medical content review and generation system built on Amazon Bedrock. T ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/14/ml-19340.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 14 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scaling, medical, content, review, Flo, Health, with, Amazon, Bedrock, –, Part</media:keywords>
</item>

<item>
<title>Accelerating software delivery with agentic QA automation using Amazon Nova Act – Part 2</title>
<link>https://news.jatlink.uk/15894</link>
<guid>https://news.jatlink.uk/15894</guid>
<description><![CDATA[ In this post, we extend that foundation to demonstrate how QA Studio addresses batch regression testing and pipeline integration through test suites that organize and parallelize execution, and a command-line interface that brings agentic testing into automated CI/CD pipelines. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/14/ML-20773.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 14 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerating, software, delivery, with, agentic, automation, using, Amazon, Nova, Act, –, Part</media:keywords>
</item>

<item>
<title>Scaling UX testing with Amazon Nova Act: A new approach to user flow analysis</title>
<link>https://news.jatlink.uk/15895</link>
<guid>https://news.jatlink.uk/15895</guid>
<description><![CDATA[ Using generative AI enables parallel execution of comprehensive user flow testing at scale. This solution demonstrates how to build a cloud-deployed UX testing platform that automatically generates test scenarios from documentation, executes user flows at scale using the intelligent navigation capabilities of Nova Act, and provides actionable insights through automated analysis. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/14/ML-19357.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 14 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scaling, testing, with, Amazon, Nova, Act:, new, approach, user, flow, analysis</media:keywords>
</item>

<item>
<title>OpenAI GPT&amp;5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock</title>
<link>https://news.jatlink.uk/15824</link>
<guid>https://news.jatlink.uk/15824</guid>
<description><![CDATA[ Today, GPT-5.6 Sol, Terra, and Luna from OpenAI are generally available on Amazon Bedrock, bringing the smartest family of models from OpenAI yet to Amazon Bedrock’s next-generation inference engine built for high-performance, security and reliability. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/13/ML-21359.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 13 Jul 2026 23:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>OpenAI, GPT-5.6, Sol, Terra, and, Luna, are, now, generally, available, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Implement on&amp;behalf&amp;of token exchange for multi&amp;tenant agents with Amazon Bedrock AgentCore Gateway</title>
<link>https://news.jatlink.uk/15806</link>
<guid>https://news.jatlink.uk/15806</guid>
<description><![CDATA[ Building multi-tenant agents with Amazon Bedrock AgentCore and Apply fine-grained access control with Bedrock AgentCore Gateway interceptors establish the conceptual foundation for on-behalf-of (OBO) token exchange in agentic systems. This post is the implementation guide. It walks through a complete multi-tenant OBO setup against Okta, shows the JSON Web Token (JWT) claim transformations on each hop, and demonstrates how audience binding produces defense in depth that scales across tenants. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/13/ML-20860.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 13 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implement, on-behalf-of, token, exchange, for, multi-tenant, agents, with, Amazon, Bedrock, AgentCore, Gateway</media:keywords>
</item>

<item>
<title>Launching UI for generative AI inference recommendations in Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/15807</link>
<guid>https://news.jatlink.uk/15807</guid>
<description><![CDATA[ In this post, we introduce the UI for optimized generative AI inference recommendations in Amazon SageMaker AI Studio, a low-code no-code (LCNC) experience. The API already gives you programmatic access to recommendations, but it assumes you know which parameters to set and how to interpret raw benchmark output. The UI removes that assumption. It guides you through preset use-case profiles, visual comparisons of results, and one-click deployment, so teams without deep infrastructure expertise can get a validated configuration on their own. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/13/ml-21345.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 13 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Launching, for, generative, inference, recommendations, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>When your brain works differently, AI isn’t a luxury—it’s accessibility</title>
<link>https://news.jatlink.uk/15804</link>
<guid>https://news.jatlink.uk/15804</guid>
<description><![CDATA[ In this post, I share how AI serves as an accessibility tool for neurodivergent professionals. The system is built on Amazon Quick on your desktop, an AI-powered desktop and web assistant that compensates for executive function gaps every day. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/13/ML-21218.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 13 Jul 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>When, your, brain, works, differently, isn’t, luxury—it’s, accessibility</media:keywords>
</item>

<item>
<title>Building an agentic AI solution at Bluesight with Amazon Bedrock</title>
<link>https://news.jatlink.uk/15805</link>
<guid>https://news.jatlink.uk/15805</guid>
<description><![CDATA[ In this post, we describe how Bluesight used two AWS engagements and Amazon Bedrock AgentCore to evolve from a single-product AI prototype to Prism, a unified agentic AI solution spanning six healthcare compliance products. Prism Assistant for ControlCheck launched in May 2026 and is already in use by 20 health systems. A more complex multi-product agentic solution is on track for later in 2026. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/13/ml-21092.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 13 Jul 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, agentic, solution, Bluesight, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Disaggregated prefill and decode for LLM inference on SageMaker HyperPod</title>
<link>https://news.jatlink.uk/15600</link>
<guid>https://news.jatlink.uk/15600</guid>
<description><![CDATA[ In this post, we show how to implement DPD with vLLM on Amazon SageMaker HyperPod using the HyperPod Inference Operator. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/08/20985-1.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 10 Jul 2026 19:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Disaggregated, prefill, and, decode, for, LLM, inference, SageMaker, HyperPod</media:keywords>
</item>

<item>
<title>Real&amp;time dental image verification with Amazon SageMaker AI at Henry Schein One</title>
<link>https://news.jatlink.uk/15595</link>
<guid>https://news.jatlink.uk/15595</guid>
<description><![CDATA[ This post describes how Henry Schein One closed that gap by building Image Verify, an AI-powered quality verification system on Amazon SageMaker AI that evaluates dental X-ray quality at the point of capture, in real time, across thousands of locations. The system went from concept to over 10,000 active locations within months and has already processed over 11 million X-rays and growing at 1.5 million per week. Henry Schein One is now scaling toward 40,000 locations globally across four regions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/10/ml-21121.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 10 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Real-time, dental, image, verification, with, Amazon, SageMaker, Henry, Schein, One</media:keywords>
</item>

<item>
<title>Build a semantic layer for agentic AI on AWS with Stardog and Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/15596</link>
<guid>https://news.jatlink.uk/15596</guid>
<description><![CDATA[ In this post we show how to build a semantic layer on AWS using Stardog’s Semantic AI Application over Amazon Aurora and Amazon Redshift, and how to run a Strands Agents agent on Amazon Bedrock AgentCore that queries the layer to answer customer 360 questions across both sources without extract, transform, and load (ETL). The same Stardog deployment works behind AWS computes (Amazon Elastic Kubernetes Service (Amazon EKS), Amazon Elastic Container Service (Amazon ECS), and AWS Lambda). We use AgentCore here because it bundles inbound auth, hosting, and tool credentials into one managed service. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/10/ml-21021.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 10 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, semantic, layer, for, agentic, AWS, with, Stardog, and, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Scaling agentic workflows with native case management in Amazon Quick Automate</title>
<link>https://news.jatlink.uk/15597</link>
<guid>https://news.jatlink.uk/15597</guid>
<description><![CDATA[ In this post, we show you how to combine case management with agentic automation capabilities in Quick Automate. We introduce case management and explore the lifecycle of cases in an agentic workflow from case creation through processing to resolution. We cover how to create and manage single or multiple cases, automatically track and update status, handle exceptions, and incorporate Human-in-the-loop (HITL) steps within workflows. We also show the case creator-processor pattern that enables dynamic scaling. Finally, we walk through how to structure case management for enterprise processes, including HITL and case tracking, through a real-life use case. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/10/ml-20703.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 10 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scaling, agentic, workflows, with, native, case, management, Amazon, Quick, Automate</media:keywords>
</item>

<item>
<title>Deploying quantized models on Amazon SageMaker AI with Unsloth</title>
<link>https://news.jatlink.uk/15598</link>
<guid>https://news.jatlink.uk/15598</guid>
<description><![CDATA[ In this post, you will learn four deployment patterns for taking models that have already been quantized with Unsloth and deploying them on AWS infrastructure. The patterns use Amazon Elastic Compute Cloud (Amazon EC2) for direct instance access, Amazon SageMaker AI inference endpoints for managed serving, and Amazon Elastic Kubernetes Service (Amazon EKS) or Amazon Elastic Container Service (Amazon ECS) when inference needs to fit into an existing container framework. You also learn operational practices for production deployments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/10/ml-20601.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 10 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploying, quantized, models, Amazon, SageMaker, with, Unsloth</media:keywords>
</item>

<item>
<title>How KTern.AI built agentic AI for SAP on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/15599</link>
<guid>https://news.jatlink.uk/15599</guid>
<description><![CDATA[ Evolving from a traditional software as a service (SaaS) platform into a next-generation agentic AI platform meant orchestrating multiple specialized agents across long-running enterprise programs. Each agent operates with persistent context, secure tool access, and production-grade reliability. We built that system on Amazon Bedrock AgentCore using the Strands Agents SDK. This post walks through how we architected it, which agents we built, and the outcomes for our customers. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/10/ml-20577.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 10 Jul 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, KTern.AI, built, agentic, for, SAP, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Fine&amp;tune NVIDIA Nemotron 3 models with Amazon SageMaker AI serverless model customization</title>
<link>https://news.jatlink.uk/15594</link>
<guid>https://news.jatlink.uk/15594</guid>
<description><![CDATA[ In this post, we explore what makes the Nemotron 3 architecture unique, walk through the fine-tuning techniques available, and show you step-by-step how to get started with serverless customization using SageMaker Studio. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/09/ml-21327.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 10 Jul 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Fine-tune, NVIDIA, Nemotron, models, with, Amazon, SageMaker, serverless, model, customization</media:keywords>
</item>

<item>
<title>Enhancing enterprise inference on Amazon SageMaker HyperPod with data capture, Hugging Face, NVMe, and Route 53 integration</title>
<link>https://news.jatlink.uk/15512</link>
<guid>https://news.jatlink.uk/15512</guid>
<description><![CDATA[ In this post, we walk through five capabilities now available in SageMaker HyperPod inference: multi-tier data capture for auditing and model improvement, direct deployment from Hugging Face Hub, local NVMe model loading for faster cold starts, automated Route 53 DNS for custom domains, and pod-level IAM through custom service accounts. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/09/ML-21090.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 09 Jul 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Enhancing, enterprise, inference, Amazon, SageMaker, HyperPod, with, data, capture, Hugging, Face, NVMe, and, Route, integration</media:keywords>
</item>

<item>
<title>MCP tool design: Practical approaches and tradeoffs</title>
<link>https://news.jatlink.uk/15511</link>
<guid>https://news.jatlink.uk/15511</guid>
<description><![CDATA[ In this post, we show where MCP tool design goes wrong and how to fix it with practical context engineering approaches. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/26/20889.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 09 Jul 2026 19:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>MCP, tool, design:, Practical, approaches, and, tradeoffs</media:keywords>
</item>

<item>
<title>Introducing Claude apps gateway for AWS</title>
<link>https://news.jatlink.uk/15448</link>
<guid>https://news.jatlink.uk/15448</guid>
<description><![CDATA[ Today, we&#039;re announcing the Claude apps gateway for AWS, a self-hosted control plane that gives organizations a single point of control over access, cost, and policy for Claude Code and Claude Desktop. In this post, we show how to set up and run Claude apps gateway for AWS with Amazon Bedrock and Claude Platform on AWS. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/02/21305.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 08 Jul 2026 23:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Claude, apps, gateway, for, AWS</media:keywords>
</item>

<item>
<title>Automatically sort and prioritize your mailboxes by using Amazon Bedrock</title>
<link>https://news.jatlink.uk/15426</link>
<guid>https://news.jatlink.uk/15426</guid>
<description><![CDATA[ In this post, we show how organizations in the public sector can automate their email management using a generative AI solution powered by Amazon Bedrock. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/26/18089.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 08 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automatically, sort, and, prioritize, your, mailboxes, using, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Manage AI applications on Mac with Jamf’s AI Governance and Amazon Bedrock</title>
<link>https://news.jatlink.uk/15429</link>
<guid>https://news.jatlink.uk/15429</guid>
<description><![CDATA[ In this post, we show how you can use Jamf’s AI Governance with Amazon Bedrock to configure, deploy, and validate managed settings for AI applications across a Mac fleet. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/08/jamf.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 08 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Manage, applications, Mac, with, Jamf’s, Governance, and, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Powering scientific discovery: BYOKG and GraphRAG for intelligent pharmaceutical research</title>
<link>https://news.jatlink.uk/15425</link>
<guid>https://news.jatlink.uk/15425</guid>
<description><![CDATA[ In this post, we explore how Graph-based Retrieval Augmented Generation (GraphRAG) is transforming scientific research by combining graph databases with generative AI. With this approach, you can accelerate discovery processes without compromising scientific integrity. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/08/ML-19455.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 08 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Powering, scientific, discovery:, BYOKG, and, GraphRAG, for, intelligent, pharmaceutical, research</media:keywords>
</item>

<item>
<title>Building and connecting a production&amp;ready ecommerce MCP server using Amazon Bedrock AgentCore and Mistral AI Studio</title>
<link>https://news.jatlink.uk/15427</link>
<guid>https://news.jatlink.uk/15427</guid>
<description><![CDATA[ In this post, you build and connect that server end to end. You will implement MCP tools, set up two-layer JSON Web Token (JWT) authentication, deploy with AWS Cloud Development Kit (AWS CDK), and connect the result to Mistral AI’s Vibe. The post also covers prerequisites, solution architecture, best practices for MCP servers and Vibe connectors, and resource cleanup. The ecommerce server that you build supports product search, order placement, review submission, and returns processing using Amazon DynamoDB for data and Amazon Cognito for identity management. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-18668/Demo MCP Vibe.mp4" length="49398" type="image/jpeg"/>
<pubDate>Wed, 08 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, and, connecting, production-ready, ecommerce, MCP, server, using, Amazon, Bedrock, AgentCore, and, Mistral, Studio</media:keywords>
</item>

<item>
<title>Securing Amazon Bedrock AgentCore Runtime with AWS WAF</title>
<link>https://news.jatlink.uk/15428</link>
<guid>https://news.jatlink.uk/15428</guid>
<description><![CDATA[ This post shows you two architecture patterns that address this problem. Both use an internet-facing ALB with AWS WAF and route traffic through a VPC Interface Endpoint to AgentCore Runtime. Pattern 1 places an AWS Lambda proxy between the ALB and the VPC Endpoint, giving you full control over request transformation. Pattern 2 targets the VPC Endpoint ENI IP addresses directly from the ALB, removing the Lambda hop entirely. You also learn how to close the direct-access backdoor with a resource policy so that traffic flows through AWS WAF only. Both patterns have been tested end-to-end with SigV4 and OAuth (Amazon Cognito JWT) authentication. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/25/20885.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 08 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Securing, Amazon, Bedrock, AgentCore, Runtime, with, AWS, WAF</media:keywords>
</item>

<item>
<title>Multi&amp;dataset Topic best practices for Amazon Quick Chat</title>
<link>https://news.jatlink.uk/15369</link>
<guid>https://news.jatlink.uk/15369</guid>
<description><![CDATA[ This post is for data architects, business intelligence (BI) engineers, and analytics engineers building or optimizing Quick Sight Topics for natural-language Chat-based exploration. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/01/21335.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Multi-dataset, Topic, best, practices, for, Amazon, Quick, Chat</media:keywords>
</item>

<item>
<title>Data modeling patterns for Amazon Quick Sight multi&amp;dataset relationships</title>
<link>https://news.jatlink.uk/15368</link>
<guid>https://news.jatlink.uk/15368</guid>
<description><![CDATA[ In this post, we shift from concepts to patterns. For each schema, you’ll find a table structure, use cases, implementation steps, and sample SQL queries. We also cover workarounds for advanced scenarios that require extra modeling steps, and close with a summary of current limitations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/29/21287-2.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Data, modeling, patterns, for, Amazon, Quick, Sight, multi-dataset, relationships</media:keywords>
</item>

<item>
<title>Build a unified semantic layer across datasets with multi&amp;dataset Topics in Amazon Quick</title>
<link>https://news.jatlink.uk/15370</link>
<guid>https://news.jatlink.uk/15370</guid>
<description><![CDATA[ In this post, we walk through how multi-dataset Topics work, explain how the chat agent uses defined relationships to generate cross-dataset queries, and demonstrate an end-to-end implementation using a retail analytics scenario in Quick Sight. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-21218/publish and share.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, unified, semantic, layer, across, datasets, with, multi-dataset, Topics, Amazon, Quick</media:keywords>
</item>

<item>
<title>Enrich your datasets with business context: Migrating from legacy Topics to semantic datasets in Amazon Quick</title>
<link>https://news.jatlink.uk/15366</link>
<guid>https://news.jatlink.uk/15366</guid>
<description><![CDATA[ In this post, we walk through what Dataset Enrichment is, how it differs from legacy Topics, and provide three migration scenarios with step-by-step guidance so you can move your business context into the dataset layer with confidence. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/07/ml-21217.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Enrich, your, datasets, with, business, context:, Migrating, from, legacy, Topics, semantic, datasets, Amazon, Quick</media:keywords>
</item>

<item>
<title>Data modeling best practices for Amazon Quick Sight multi&amp;dataset relationships</title>
<link>https://news.jatlink.uk/15367</link>
<guid>https://news.jatlink.uk/15367</guid>
<description><![CDATA[ Today, we are excited to announce Multi-Dataset Relationships in Amazon Quick Sight. This new capability lets you define logical relationships between Quick Sight datasets and perform runtime joins at query time. Instead of flattening tables ahead of time, you keep each table as its own Quick Sight dataset and declare how those datasets relate to one another inside a Quick Sight Topic. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/29/21287-1.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Data, modeling, best, practices, for, Amazon, Quick, Sight, multi-dataset, relationships</media:keywords>
</item>

<item>
<title>How AWS Finance teams reclaimed hundreds of hours with Amazon Quick</title>
<link>https://news.jatlink.uk/15349</link>
<guid>https://news.jatlink.uk/15349</guid>
<description><![CDATA[ In this post, we show how AWS Finance used chat agents and Flows in Amazin Quick to transform two of their most time-consuming workflows. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/07/ML-20844.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 18:00:18 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, AWS, Finance, teams, reclaimed, hundreds, hours, with, Amazon, Quick</media:keywords>
</item>

<item>
<title>Build a serverless image editing agent with Amazon Bedrock AgentCore harness</title>
<link>https://news.jatlink.uk/15346</link>
<guid>https://news.jatlink.uk/15346</guid>
<description><![CDATA[ This post walks through building a serverless image editor where users upload a photo, describe an edit in plain English, and receive the result in seconds. The agent runs on AgentCore harness without custom orchestration code. We deploy the full solution, including authentication, encrypted storage, three image editing tools, and a React frontend, with a single deployment command. The infrastructure is defined using AWS Cloud Development Kit (AWS CDK). ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-20805/Harness-Image-Editing-DemoVideo-Shorter.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, serverless, image, editing, agent, with, Amazon, Bedrock, AgentCore, harness</media:keywords>
</item>

<item>
<title>Monitoring discriminative ML models using Amazon SageMaker AI with MLflow</title>
<link>https://news.jatlink.uk/15347</link>
<guid>https://news.jatlink.uk/15347</guid>
<description><![CDATA[ Implementing a data and model monitoring solution is necessary to maintain prediction accuracy and help achieve the best outcome for your machine learning use case. This post shows how you can use open source Evidently together with Amazon SageMaker AI to generate monitoring reports, organize and compare the results in MLflow, scale through pipelines, and trigger drift notifications. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/24/20699.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Monitoring, discriminative, models, using, Amazon, SageMaker, with, MLflow</media:keywords>
</item>

<item>
<title>Build an AI&amp;powered AWS support companion with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/15348</link>
<guid>https://news.jatlink.uk/15348</guid>
<description><![CDATA[ In this post, you build an AWS Support Companion using Amazon Bedrock AgentCore. The agent uses Strands Agents as the orchestration framework and connects to AWS services through the Model Context Protocol (MCP). By the end, you have a working agent that can analyze CloudWatch logs, search AWS documentation, query community knowledge from AWS re:Post, and create support cases, all from a single conversational interface. The solution deploys with a single script using AWS CloudFormation and includes a web frontend built on AWS Amplify for interacting with the agent. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/07/ml-19981.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, AI-powered, AWS, support, companion, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Teaching models to forget: Selective unlearning with Amazon Nova</title>
<link>https://news.jatlink.uk/15301</link>
<guid>https://news.jatlink.uk/15301</guid>
<description><![CDATA[ In this post, we introduce Reverse Direct Preference Optimization (rDPO), the novel unlearning technique behind Amazon Nova Customizable Content Moderation Settings (CCMS), and show how it reduces over-deflection while preserving model quality. We also provide pointers for customers who want to apply these preference optimization techniques to their own experiments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/06/ml-21116.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 02:00:16 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Teaching, models, forget:, Selective, unlearning, with, Amazon, Nova</media:keywords>
</item>

<item>
<title>From Hugging Face to Amazon SageMaker Studio in one click</title>
<link>https://news.jatlink.uk/15300</link>
<guid>https://news.jatlink.uk/15300</guid>
<description><![CDATA[ Today, we’re excited to announce a deep-link integration between Hugging Face and Amazon SageMaker AI. Developers can now go from model discovery to hands-on experimentation in SageMaker Studio with a single selection. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/06/ml-21254.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 07 Jul 2026 02:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, Hugging, Face, Amazon, SageMaker, Studio, one, click</media:keywords>
</item>

<item>
<title>Run MiniMax models on Amazon Bedrock</title>
<link>https://news.jatlink.uk/15287</link>
<guid>https://news.jatlink.uk/15287</guid>
<description><![CDATA[ In this post, we walk through how to get started with MiniMax models on Amazon Bedrock, including the capabilities supported by these models, the service tiers available, how on-demand inference scales to handle your workloads, and the different APIs you can use to access them. Using these models, customers can build agentic applications, long-context document analysis pipelines, and software engineering workflows, all backed by the security and operational guarantees of AWS. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/06/ML-21143.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 06 Jul 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Run, MiniMax, models, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Automatically redact PII in images with Amazon Nova</title>
<link>https://news.jatlink.uk/15271</link>
<guid>https://news.jatlink.uk/15271</guid>
<description><![CDATA[ In this post, we present a multi-step pipeline directed by Amazon Nova, which uses its contextual vision reasoning to coordinate complementary tools, including Meta’s open-source Segment Anything Model (SAM 3) deployed on Amazon SageMaker AI for pixel-level segmentation, and Amazon Textract for optical character recognition (OCR). This pipeline is designed to provide comprehensive and compliant PII redaction even for challenging edge cases such as fingerprints, ID cards, or license plates in arbitrary orientations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/20185.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 06 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automatically, redact, PII, images, with, Amazon, Nova</media:keywords>
</item>

<item>
<title>Streaming benchmark and recommendation results to MLflow with Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/15272</link>
<guid>https://news.jatlink.uk/15272</guid>
<description><![CDATA[ In this post, you learn how to use the new MLflow integration with Amazon SageMaker AI optimized inference recommendation jobs and Amazon SageMaker AI benchmark jobs to automatically stream experiment data into a unified tracking interface. This integration streams metrics, parameters, and charts into your serverless Amazon SageMaker MLflow App in real time and you get a unified experiment tracking experience. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/30/21187.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 06 Jul 2026 18:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Streaming, benchmark, and, recommendation, results, MLflow, with, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Deploying Multi&amp;Turn RL Infrastructure for Amazon Nova on Amazon SageMaker HyperPod</title>
<link>https://news.jatlink.uk/15270</link>
<guid>https://news.jatlink.uk/15270</guid>
<description><![CDATA[ In this post, you deploy a two-phase infrastructure for multi-turn RL using Amazon Nova Forge on Amazon SageMaker HyperPod. By the end, you have an event-driven pipeline that starts training when you upload data to Amazon Simple Storage Service (Amazon S3). The training job teaches the model to play Wordle, a placeholder for your own RL task. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/25/20450.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 06 Jul 2026 18:00:16 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Deploying, Multi-Turn, Infrastructure, for, Amazon, Nova, Amazon, SageMaker, HyperPod</media:keywords>
</item>

<item>
<title>Best practices for multi&amp;turn reinforcement learning in Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/15024</link>
<guid>https://news.jatlink.uk/15024</guid>
<description><![CDATA[ In this post, we share best practices for reliable multi-turn RL training. We cover how to build a training environment you can trust, set up an external evaluation, design a reward aligned with the end task, manage what changes once the agent runs for multiple turns, and monitor the metrics that tell you when to iterate. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/02/ml-21260.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 02 Jul 2026 22:00:19 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Best, practices, for, multi-turn, reinforcement, learning, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>How Amazon Bedrock catches AI&amp;generated phishing</title>
<link>https://news.jatlink.uk/15023</link>
<guid>https://news.jatlink.uk/15023</guid>
<description><![CDATA[ Social engineering through phishing remains one of the most common tactics for launching cyberattacks. AI-generated phishing email messages now pose a new challenge for security teams managing email systems, significantly raising the risk because of their advanced sophistication. Modern social engineers use generative AI and open source intelligence (OSINT) to craft thousands of unique messages […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/02/ML-19725.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 02 Jul 2026 22:00:18 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Amazon, Bedrock, catches, AI-generated, phishing</media:keywords>
</item>

<item>
<title>Simplify model selection in Amazon Bedrock with the open source Model Profiler</title>
<link>https://news.jatlink.uk/14940</link>
<guid>https://news.jatlink.uk/14940</guid>
<description><![CDATA[ The Amazon Bedrock Model Profiler is an open source tool that aggregates model metadata from multiple AWS APIs and external sources into a single, searchable interface. In this post, you’ll learn what the Model Profiler provides, the real-world scenarios it supports, and how to deploy it in your own environment in under five minutes. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/20648.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Simplify, model, selection, Amazon, Bedrock, with, the, open, source, Model, Profiler</media:keywords>
</item>

<item>
<title>Accelerate protein design with BoltzGen on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/14941</link>
<guid>https://news.jatlink.uk/14941</guid>
<description><![CDATA[ In this post, we demonstrate how to deploy BoltzGen on SageMaker AI and run an end-to-end protein design experiment. By the end of the walkthrough, you have a working setup that scales from quick validation runs to production batch processing. The setup offers two execution modes for different stages of research and uses step-level caching to reduce compute expenses during iterative workflows. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/01/ml-20375.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerate, protein, design, with, BoltzGen, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>HippoRAG: Neurobiologically inspired RAG using Amazon Bedrock, Amazon Neptune, and personalized PageRank</title>
<link>https://news.jatlink.uk/14938</link>
<guid>https://news.jatlink.uk/14938</guid>
<description><![CDATA[ In this post, we demonstrate how to implement HippoRAG using a comprehensive AWS stack. We use Amazon Bedrock for LLM capabilities, Amazon Neptune for graph database functionality, Amazon Neptune Analytics for advanced graph algorithms including Personalized PageRank, and Amazon Titan Embeddings for vector representations. This implementation showcases how to build and deploy HippoRAG within AWS infrastructure for enterprise-scale applications. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/19373.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>HippoRAG:, Neurobiologically, inspired, RAG, using, Amazon, Bedrock, Amazon, Neptune, and, personalized, PageRank</media:keywords>
</item>

<item>
<title>How Inscribe uses Amazon Bedrock to stop document fraud in seconds</title>
<link>https://news.jatlink.uk/14939</link>
<guid>https://news.jatlink.uk/14939</guid>
<description><![CDATA[ In this post, you will learn how Inscribe developed an agentic AI system using Amazon Bedrock that reasons across documents the way an expert fraud analyst would. With this new agentic AI system, Inscribe now detects tampered, fabricated, and AI-generated financial documents in under 90 seconds. This is a 20x improvement over traditional manual review, while maintaining the accuracy and explainability required by financial services regulations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/19301.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Inscribe, uses, Amazon, Bedrock, stop, document, fraud, seconds</media:keywords>
</item>

<item>
<title>Building a serverless A2A gateway for agent discovery, routing, and access control</title>
<link>https://news.jatlink.uk/14936</link>
<guid>https://news.jatlink.uk/14936</guid>
<description><![CDATA[ In this post, you will learn how to build a serverless A2A gateway on AWS that hosts multiple agents behind a single domain using path-based routing (/agents/{agentId}). Standard A2A clients work without modification. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/01/ml-20635.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 22:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, serverless, A2A, gateway, for, agent, discovery, routing, and, access, control</media:keywords>
</item>

<item>
<title>Structured memory filtering with metadata in AgentCore Memory</title>
<link>https://news.jatlink.uk/14937</link>
<guid>https://news.jatlink.uk/14937</guid>
<description><![CDATA[ In this post, you will learn how metadata works across configuration, ingestion, and retrieval, explore enterprise use cases including multi-agent and multi-tenant architectures, and discover best practices for implementation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/20840.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 22:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Structured, memory, filtering, with, metadata, AgentCore, Memory</media:keywords>
</item>

<item>
<title>Run NVIDIA Nemotron and OpenAI GPT OSS models on Amazon Bedrock in AWS GovCloud (US)</title>
<link>https://news.jatlink.uk/14935</link>
<guid>https://news.jatlink.uk/14935</guid>
<description><![CDATA[ We&#039;re excited to introduce US-based frontier open-weight models in AWS GovCloud (US). With this release, Amazon Bedrock now supports OpenAI’s open-weight GPT OSS models (120B and 20B) and NVIDIA Nemotron (Nano 9B v2, Nano 12B v2, Nano 30B, Super 120B) models. In this post, we cover these models and their capabilities, the inference options for data residency, the available service tiers and how to get started. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/01/ml-21215.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 22:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Run, NVIDIA, Nemotron, and, OpenAI, GPT, OSS, models, Amazon, Bedrock, AWS, GovCloud, US</media:keywords>
</item>

<item>
<title>Safely Releasing Frontier Models to Customers</title>
<link>https://news.jatlink.uk/14886</link>
<guid>https://news.jatlink.uk/14886</guid>
<description><![CDATA[ It’s our goal for AWS to be the most secure place to run any workload, and in support of that we’ve been deeply investing in security across our services since AWS&#039;s inception more than two decades ago. Our AI services like Amazon Bedrock are built on this foundation and with the same focus.  ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/20/21306.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 01 Jul 2026 06:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Safely, Releasing, Frontier, Models, Customers</media:keywords>
</item>

<item>
<title>Introducing Claude Sonnet 5 on AWS: Anthropic’s most capable Sonnet model</title>
<link>https://news.jatlink.uk/14859</link>
<guid>https://news.jatlink.uk/14859</guid>
<description><![CDATA[ Today, we’re excited to announce the availability of Anthropic’s most advanced Sonnet model, Claude Sonnet 5, on Amazon Bedrock and Claude Platform on AWS. Claude Sonnet 5 is the first Sonnet model of Anthropic’s latest generation and represents a meaningful step forward. It delivers top-tier intelligence at Sonnet pricing for coding, agents, and everyday professional […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/25/21192.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 30 Jun 2026 22:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Claude, Sonnet, AWS:, Anthropic’s, most, capable, Sonnet, model</media:keywords>
</item>

<item>
<title>Building bilingual NER for cargo logistics with Amazon Bedrock</title>
<link>https://news.jatlink.uk/14841</link>
<guid>https://news.jatlink.uk/14841</guid>
<description><![CDATA[ In this post, we share the technical approach using token-based distillation, lessons learned, and deployment architecture. If you face similar bilingual NER challenges, you can benefit from IBS Software’s experience with the Amazon Bedrock knowledge distillation capabilities. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/30/ml-20433.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 30 Jun 2026 18:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, bilingual, NER, for, cargo, logistics, with, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Implementing resilience patterns with Amazon Bedrock and LLM gateway</title>
<link>https://news.jatlink.uk/14839</link>
<guid>https://news.jatlink.uk/14839</guid>
<description><![CDATA[ In this post, you will learn five practical patterns for building resilient generative AI applications on AWS, progressing from native Amazon Bedrock features to multi-model orchestration using an LLM gateway. These patterns address real-world challenges such as quota exhaustion during unexpected traffic surges, maximizing availability through geographic distribution of inference, and helping prevent noisy neighbor problems in multi-tenant environments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/19331.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 30 Jun 2026 18:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implementing, resilience, patterns, with, Amazon, Bedrock, and, LLM, gateway</media:keywords>
</item>

<item>
<title>How Outpost VFX Uses AWS to Accelerate AI Model Training for Visual Effects</title>
<link>https://news.jatlink.uk/14840</link>
<guid>https://news.jatlink.uk/14840</guid>
<description><![CDATA[ In this post, we explore how Outpost VFX achieved 8x faster training speeds using AWS infrastructure to transform their face replacement workflow, the technical architecture they implemented to overcome single-GPU limitations, and the measurable results achieved through AWS multi-GPU training. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/30/ml-20295.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 30 Jun 2026 18:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Outpost, VFX, Uses, AWS, Accelerate, Model, Training, for, Visual, Effects</media:keywords>
</item>

<item>
<title>Fine&amp;tune Amazon Nova models for accurate email data extraction</title>
<link>https://news.jatlink.uk/14842</link>
<guid>https://news.jatlink.uk/14842</guid>
<description><![CDATA[ In this post, you&#039;ll learn how fine-tuning Amazon Nova models using Amazon SageMaker AI addresses these specific issues by teaching the models to recognize your exact data patterns, distinguish between similar fields, and process information more efficiently—achieving up to 94.77% extraction accuracy while reducing costs 50%. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/30/ml-20559.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 30 Jun 2026 18:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Fine-tune, Amazon, Nova, models, for, accurate, email, data, extraction</media:keywords>
</item>

<item>
<title>Simplify multi&amp;account access to Amazon Bedrock models with managed entitlements</title>
<link>https://news.jatlink.uk/14838</link>
<guid>https://news.jatlink.uk/14838</guid>
<description><![CDATA[ In this post, we show you how to use managed entitlements for Amazon Bedrock to subscribe once from a central account and distribute model access across your organization. This approach removes the need for AWS Marketplace permissions in workload accounts. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/29/20435.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 30 Jun 2026 18:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Simplify, multi-account, access, Amazon, Bedrock, models, with, managed, entitlements</media:keywords>
</item>

<item>
<title>Build generative UI for AI agents on Amazon Bedrock AgentCore with the AG&amp;UI protocol</title>
<link>https://news.jatlink.uk/14837</link>
<guid>https://news.jatlink.uk/14837</guid>
<description><![CDATA[ This post walks through how AG-UI integrates into the Fullstack AgentCore Solution Template (FAST) to build interactive agent frontends on Amazon Bedrock AgentCore. We then show how CopilotKit extends this with generative UI, shared state, and human-in-the-loop interactions, all deployed on Amazon Bedrock AgentCore. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20863/output_progressive.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 30 Jun 2026 18:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, generative, for, agents, Amazon, Bedrock, AgentCore, with, the, AG-UI, protocol</media:keywords>
</item>

<item>
<title>Build an agentic AI healthcare claims pipeline with Amazon Bedrock and AWS HealthLake</title>
<link>https://news.jatlink.uk/14764</link>
<guid>https://news.jatlink.uk/14764</guid>
<description><![CDATA[ In this post, we show you how to build an automated claims processing pipeline using two key Amazon Bedrock capabilities: Amazon Bedrock Data Automation for intelligent document extraction from healthcare claim forms, and Amazon Bedrock AgentCore for hosting an AI agent that validates and transforms the extracted data into FHIR (Fast Healthcare Interoperable Resources) resources in AWS HealthLake. You will learn how to combine these services to create an end-to-end workflow that reduces manual processing while maintaining accuracy through automated validation checks. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/29/ml-19409.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 29 Jun 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, agentic, healthcare, claims, pipeline, with, Amazon, Bedrock, and, AWS, HealthLake</media:keywords>
</item>

<item>
<title>Debugging production agents with Amazon Bedrock AgentCore Observability</title>
<link>https://news.jatlink.uk/14765</link>
<guid>https://news.jatlink.uk/14765</guid>
<description><![CDATA[ In this post, you learn how to debug production agent failures using built-in observability capabilities. We walk through common failure patterns, show how to analyze agent behavior with traces and metrics, and provide structured workflows for resolving issues such as infinite loops and tool invocation failures. This is Part 1 of a two-part series. Part 2 covers performance optimization and memory management. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/20441.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 29 Jun 2026 22:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Debugging, production, agents, with, Amazon, Bedrock, AgentCore, Observability</media:keywords>
</item>

<item>
<title>Implement a backup strategy for Amazon Quick Sight BI assets</title>
<link>https://news.jatlink.uk/14761</link>
<guid>https://news.jatlink.uk/14761</guid>
<description><![CDATA[ In this post, we cover best practices for implementing an effective backup strategy for BI assets in Quick Sight. We start by covering the options for selecting the assets to include in your backup, then explain the high-level APIs available for that purpose, and finalize with sample code to help you get started quickly. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/29/ml-20472.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 29 Jun 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implement, backup, strategy, for, Amazon, Quick, Sight, assets</media:keywords>
</item>

<item>
<title>Pair Nova 2 Lite with Claude for cost&amp;optimized document processing</title>
<link>https://news.jatlink.uk/14762</link>
<guid>https://news.jatlink.uk/14762</guid>
<description><![CDATA[ In this post, we show how pairing Amazon Nova 2 Lite with Anthropic’s Claude Sonnet 4.6 delivers an efficient solution for digitizing scanned documents at scale. We built a two-model pipeline on Amazon Bedrock for digitizing scanned yearbook pages. Amazon Nova 2 Lite handles native multimodal extraction in a single call: detecting photos, extracting visible names with coordinates, and returning page-level metadata. Claude Sonnet 4.6 then performs spatial reasoning to match names to faces based on page layout. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/29/ml-20681.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 29 Jun 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Pair, Nova, Lite, with, Claude, for, cost-optimized, document, processing</media:keywords>
</item>

<item>
<title>Multi&amp;tenant LLM analytics with row&amp;level security: How we built a secure agent on AWS</title>
<link>https://news.jatlink.uk/14763</link>
<guid>https://news.jatlink.uk/14763</guid>
<description><![CDATA[ In this post, we show you how PAR built a production-ready multi-tenant LLM analytics system that enforces row-level security through a three-layer architecture: cryptographic request signing with AWS SigV4, semantic validation on Amazon Bedrock, and programmatic data isolation via Split-Plane SQL. We demonstrate how each layer operates independently to reduce the risk of cross-tenant data exposure, even when the LLM itself is compromised or manipulated. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/25/19651.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 29 Jun 2026 22:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Multi-tenant, LLM, analytics, with, row-level, security:, How, built, secure, agent, AWS</media:keywords>
</item>

<item>
<title>How Cara pioneers domain&amp;specific AI for enterprise insurance brokerages with AWS</title>
<link>https://news.jatlink.uk/14557</link>
<guid>https://news.jatlink.uk/14557</guid>
<description><![CDATA[ In this post, we explore how Cara, built in cooperation with AWS, addresses these challenges. We walk through the technical design decisions and the AWS services that support the solution. We also share measurable outcomes Cara has delivered for enterprise brokerages. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/24/20401.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 26 Jun 2026 18:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Cara, pioneers, domain-specific, for, enterprise, insurance, brokerages, with, AWS</media:keywords>
</item>

<item>
<title>Production&amp;grade AI agents for financial compliance: Lessons from Stripe</title>
<link>https://news.jatlink.uk/14558</link>
<guid>https://news.jatlink.uk/14558</guid>
<description><![CDATA[ In this post, you learn how Stripe built a production-grade AI agent system for financial compliance. We cover the technical architecture of Stripe’s ReAct agent framework and the infrastructure decisions behind a dedicated agent service. We also discuss the role of human oversight in maintaining accountability, and key lessons about task decomposition, orchestration patterns, and cost optimization through prompt caching. By the end, you will understand how to design agentic systems that scale compliance operations without compromising quality or auditability. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/26/ml-20542.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 26 Jun 2026 18:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Production-grade, agents, for, financial, compliance:, Lessons, from, Stripe</media:keywords>
</item>

<item>
<title>Build interactive PDF text extraction from Amazon S3</title>
<link>https://news.jatlink.uk/14556</link>
<guid>https://news.jatlink.uk/14556</guid>
<description><![CDATA[ In this post, you’ll build a server that extracts text from PDF files in Amazon S3 in real time. This protocol-based approach provides programmatic document access. You’ll walk through the architecture, set up the server, and run interactive document queries. Along the way, you’ll compare this approach with Amazon Textract so you can decide which tool fits your workload. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/23/19835.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 26 Jun 2026 18:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, interactive, PDF, text, extraction, from, Amazon</media:keywords>
</item>

<item>
<title>Retrofit, don’t rebuild: Agentic overlays for transforming legacy enterprise services</title>
<link>https://news.jatlink.uk/14484</link>
<guid>https://news.jatlink.uk/14484</guid>
<description><![CDATA[ In this technical collaboration between AWS and the authors, we present a pragmatic solution: agentic overlays. Agentic overlays are thin wrapper layers that transform traditional REST-based services into agents capable of participating in A2A interactions. They also expose REST APIs as tools compatible with the Model Context Protocol (MCP). Together, they let enterprises add A2A capabilities to existing REST services without rewriting business logic, without duplicating code, and without running parallel infrastructures. This reduces agent sprawl in the infrastructure by reusing existing services as agents. We provide reference architectures and sample code that show how to build agentic overlays. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/25/ml-20189.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 25 Jun 2026 22:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Retrofit, don’t, rebuild:, Agentic, overlays, for, transforming, legacy, enterprise, services</media:keywords>
</item>

<item>
<title>Building agentic AI applications with a modern data mesh strategy on AWS</title>
<link>https://news.jatlink.uk/14472</link>
<guid>https://news.jatlink.uk/14472</guid>
<description><![CDATA[ This post shows how to build a governed, serverless data mesh on AWS that provides the secure, scalable data foundation production agentic AI requires. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/25/ml-20469.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 25 Jun 2026 18:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, agentic, applications, with, modern, data, mesh, strategy, AWS</media:keywords>
</item>

<item>
<title>Optimize model training on Amazon SageMaker AI with NVIDIA Blackwell</title>
<link>https://news.jatlink.uk/14469</link>
<guid>https://news.jatlink.uk/14469</guid>
<description><![CDATA[ This post shows you how to configure training jobs on Amazon SageMaker AI to get the most out of Blackwell’s architecture on AWS. You learn how to select batch sizes and sequence lengths that take advantage of Blackwell’s expanded memory, choose the right precision format for your model size (1B to 64B parameters), and apply activation checkpointing strategically. By the end, you have a practical framework for tuning your training configuration and launching distributed training jobs on P6-B200 instances. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/20239.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 25 Jun 2026 18:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Optimize, model, training, Amazon, SageMaker, with, NVIDIA, Blackwell</media:keywords>
</item>

<item>
<title>Implementing super resolution by deploying SeedVR2 on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/14470</link>
<guid>https://news.jatlink.uk/14470</guid>
<description><![CDATA[ In this post, we demonstrate how to implement video upscaling using SeedVR2 on SageMaker AI. We cover the solution architecture, walk through the deployment steps, and show performance comparisons that highlight the quality improvements and processing efficiency you can achieve. By the end of this post, you’ll have the practical knowledge needed to implement this super resolution solution. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/25/ml-19605.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 25 Jun 2026 18:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implementing, super, resolution, deploying, SeedVR2, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Build self&amp;service AWS Health analytics to find actionable health insights with AI agents powered by Amazon Bedrock</title>
<link>https://news.jatlink.uk/14471</link>
<guid>https://news.jatlink.uk/14471</guid>
<description><![CDATA[ In this post, we show you how to build Chaplin (Customer Health and Planned Lifecycle Intelligence Nexus), an open source solution that uses AI agents exposed through the Model Context Protocol (MCP) to provide self-service health event analytics. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/20336.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 25 Jun 2026 18:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, self-service, AWS, Health, analytics, find, actionable, health, insights, with, agents, powered, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Build a healthcare appointment agent with Amazon Nova 2 Sonic</title>
<link>https://news.jatlink.uk/14393</link>
<guid>https://news.jatlink.uk/14393</guid>
<description><![CDATA[ In this post, you will learn how to build a voice agent that handles appointment reminder conversations using Amazon Nova 2 Sonic and Amazon Bedrock AgentCore. The agent authenticates patients by voice, manages appointments (confirm, cancel, or reschedule), collects pre-visit health information, and escalates to human staff when needed. You handle routine calls at scale, which can help reduce no-show rates. This sample focuses on the agentic side of the problem: voice conversation and tool orchestration. A browser-based interface is included for testing. To connect the agent to actual phone lines for outbound dialing, you would integrate a telephony service such as Amazon Connect Customer. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/24/ML-19583.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 24 Jun 2026 22:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, healthcare, appointment, agent, with, Amazon, Nova, Sonic</media:keywords>
</item>

<item>
<title>AI&amp;powered BI with Snowflake and Amazon Quick</title>
<link>https://news.jatlink.uk/14394</link>
<guid>https://news.jatlink.uk/14394</guid>
<description><![CDATA[ In this post, you will learn how to build an end-to-end integration between Snowflake semantic views and Amazon Quick. The sample data is user review data for a media company. You start by loading movie review data from Amazon Simple Storage Service (Amazon S3) into Snowflake, define a semantic view in SQL to add business meaning, explore it with natural-language queries through Cortex Analyst, and then generate an Amazon Quick dataset and dashboard. The dataset can be created manually or with a provided automation script. By the end, your BI team or AI team can ask natural-language questions against a governed data layer and trust that every response reflects the same business logic. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/09/ML-20803-2.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 24 Jun 2026 22:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AI-powered, with, Snowflake, and, Amazon, Quick</media:keywords>
</item>

<item>
<title>Huntington Bank: Redacting sensitive data from 400M+ documents with AWS</title>
<link>https://news.jatlink.uk/14392</link>
<guid>https://news.jatlink.uk/14392</guid>
<description><![CDATA[ In this post, we walk through how Huntington built a scalable AWS solution to detect and redact Personally Identifiable Information (PII) and Payment Card Industry (PCI) data from over 400 million documents, reducing processing time from years to just a few months while achieving 95%+ redaction accuracy. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/24/ML-19309.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 24 Jun 2026 22:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Huntington, Bank:, Redacting, sensitive, data, from, 400M, documents, with, AWS</media:keywords>
</item>

<item>
<title>How Loka Built a Natural, Low&amp;Latency Voice Agent with Amazon Nova 2 Sonic</title>
<link>https://news.jatlink.uk/14378</link>
<guid>https://news.jatlink.uk/14378</guid>
<description><![CDATA[ In this post, we demonstrate the architecture and approach Loka used to solve a common frustration: robotic, slow voice assistants that cause customers to hang up, damaging brand reputation and driving up support costs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20376/demo.mp4" length="49398" type="image/jpeg"/>
<pubDate>Wed, 24 Jun 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Loka, Built, Natural, Low-Latency, Voice, Agent, with, Amazon, Nova, Sonic</media:keywords>
</item>

<item>
<title>Build a protein research copilot with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/14300</link>
<guid>https://news.jatlink.uk/14300</guid>
<description><![CDATA[ This post shows you how to build a conversational protein research assistant that combines three capabilities: Natural language query parsing to extract structured search parameters, vector similarity search over protein embeddings using a specialized language model and ai-generated scientific summaries of search results. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/19630.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 23 Jun 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, protein, research, copilot, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Shared infrastructure, isolated tenants: Pool model multi&amp;tenancy with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/14301</link>
<guid>https://news.jatlink.uk/14301</guid>
<description><![CDATA[ In this post, you will learn patterns for implementing production-ready multi-tenant systems using Amazon Bedrock AgentCore. You will see these patterns demonstrated through healthcare AI agents that serve multiple clinics and hospitals. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/19774.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 23 Jun 2026 18:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Shared, infrastructure, isolated, tenants:, Pool, model, multi-tenancy, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Building pay&amp;per&amp;intelligence for AI agents: How Ampersend uses Amazon Bedrock AgentCore Payments</title>
<link>https://news.jatlink.uk/14237</link>
<guid>https://news.jatlink.uk/14237</guid>
<description><![CDATA[ In this post, you will learn how Ampersend built a pay-per-intelligence routing layer on top of Amazon Bedrock AgentCore Payments. AI agents autonomously route tasks to the most effective model, pay per request, and operate within spending budgets. You will also see how the two-hop payment pattern works end-to-end and how to get started with your own implementation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/18/ML-21061.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 22 Jun 2026 22:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, pay-per-intelligence, for, agents:, How, Ampersend, uses, Amazon, Bedrock, AgentCore, Payments</media:keywords>
</item>

<item>
<title>Embed the world: Multimodal AI for searchable aerial imagery at scale</title>
<link>https://news.jatlink.uk/14222</link>
<guid>https://news.jatlink.uk/14222</guid>
<description><![CDATA[ In this post, we walk through the problem space, our architecture on Amazon Bedrock and Amazon OpenSearch Serverless, the evaluation methodology we built on OpenStreetMap ground truth, four experiments that compared embedding models, fusion strategies, captioning, and search methods, and the practical guidance you can apply when building a similar system. You’ll learn which design choices move the needle for geospatial semantic search, including why Amazon Nova Multimodal Embeddings delivered the highest F1 scores across both benchmark queries in our evaluation. The work described here evolved into Vexcel Intelligence, a searchable imagery product. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/02/20912.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 22 Jun 2026 18:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Embed, the, world:, Multimodal, for, searchable, aerial, imagery, scale</media:keywords>
</item>

<item>
<title>Running ComfyUI workflows on Amazon SageMaker AI processing jobs</title>
<link>https://news.jatlink.uk/14223</link>
<guid>https://news.jatlink.uk/14223</guid>
<description><![CDATA[ In this post, we walk you through how to deploy ComfyUI workflows on Amazon SageMaker AI processing jobs to generate hundreds of high-quality images in a single batch. You learn how to set up the infrastructure using AWS Cloud Development Kit (AWS CDK), configure GPU-accelerated processing, and automate image generation at scale. You can then adapt this solution to your ComfyUI workflows specific to your needs. We will guide you through a practical, step-by-step process to automate ComfyUI workflows to generate hundreds of high-quality images in a single batch empowering you to scale your creative pipeline. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/22/ml-19966.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 22 Jun 2026 18:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Running, ComfyUI, workflows, Amazon, SageMaker, processing, jobs</media:keywords>
</item>

<item>
<title>Introducing Web Search on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/14022</link>
<guid>https://news.jatlink.uk/14022</guid>
<description><![CDATA[ Web Search on Amazon Bedrock AgentCore is now generally available. In this post, we walk through what makes Web Search on Amazon Bedrock AgentCore different, why it matters, and how to wire it in with a few lines of code. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/17/ml-21231.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 19 Jun 2026 17:00:18 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Web, Search, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Accelerate campaign workflow with insights from Adobe Marketing Agent for Amazon Quick</title>
<link>https://news.jatlink.uk/14023</link>
<guid>https://news.jatlink.uk/14023</guid>
<description><![CDATA[ This post shows how to enable Adobe Marketing Agent for Amazon Quick using a Model Context Protocol (MCP). We walk you through how to configure the integration, authenticate using your Adobe credentials, and get the latest insights in Amazon Quick. The sample workflow returns audience rankings, loyalty segment summaries, journey usage, and conflict recommendations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/18/ML-21232-1-1119x630.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 19 Jun 2026 17:00:18 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerate, campaign, workflow, with, insights, from, Adobe, Marketing, Agent, for, Amazon, Quick</media:keywords>
</item>

<item>
<title>Monitor and debug generative AI inference with SageMaker detailed metrics and Insights dashboard on CloudWatch</title>
<link>https://news.jatlink.uk/13973</link>
<guid>https://news.jatlink.uk/13973</guid>
<description><![CDATA[ Amazon SageMaker AI provides fully managed real-time inference hosting for machine learning models. You deploy a model to a SageMaker endpoint backed by one or more compute instances, and SageMaker handles provisioning and scaling. SageMaker supports multiple endpoint architectures. This post focuses on the two most relevant to generative AI workloads with detailed observability: Single-model endpoints (SME) and Inference component (IC) endpoints. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/18/ml-21272.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 19 Jun 2026 01:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Monitor, and, debug, generative, inference, with, SageMaker, detailed, metrics, and, Insights, dashboard, CloudWatch</media:keywords>
</item>

<item>
<title>Amazon Bedrock AgentCore harness is now generally available: Go from idea to production&amp;grade agent in minutes</title>
<link>https://news.jatlink.uk/13955</link>
<guid>https://news.jatlink.uk/13955</guid>
<description><![CDATA[ Today, Amazon Bedrock AgentCore harness is generally available. Two API calls (CreateHarness to define an agent, and InvokeHarness to run it), and you have an agent running in seconds. The agent runs in its own isolated environment with a filesystem and shell, so it can read files, run commands, and write code safely. It remembers users and conversations across sessions, picks up skills you point it at (including the AWS-curated catalog), browses the web, calls your tools through gateway or MCP, and switches model providers mid-session without losing context. Every step streams back to you in real time and is automatically traced to Amazon CloudWatch. You don’t need to write orchestration code or build a container, unless you want to. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/17/ml-20804.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 18 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Bedrock, AgentCore, harness, now, generally, available:, from, idea, production-grade, agent, minutes</media:keywords>
</item>

<item>
<title>Get back hours every day with autonomous agents in Amazon Quick</title>
<link>https://news.jatlink.uk/13886</link>
<guid>https://news.jatlink.uk/13886</guid>
<description><![CDATA[ Today, Quick gets even more powerful: new autonomous agents that work continuously on your behalf, an activity feed that helps you prioritize your most important work, and the ability to find insights across every data source your business runs on from a single question. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/17/ml-21220.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 18 Jun 2026 01:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Get, back, hours, every, day, with, autonomous, agents, Amazon, Quick</media:keywords>
</item>

<item>
<title>Amazon SageMaker AI Async Inference now supports inline request payloads</title>
<link>https://news.jatlink.uk/13885</link>
<guid>https://news.jatlink.uk/13885</guid>
<description><![CDATA[ Today, we’re announcing inline payload support for Amazon SageMaker AI Async Inference. Customers can now send inference payloads directly in the request body of the InvokeEndpointAsync API, removing the need to upload input data to Amazon Simple Storage Service (Amazon S3) before each invocation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/17/21184.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 18 Jun 2026 01:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, SageMaker, Async, Inference, now, supports, inline, request, payloads</media:keywords>
</item>

<item>
<title>Context intelligence for your data and AI agents at scale</title>
<link>https://news.jatlink.uk/13871</link>
<guid>https://news.jatlink.uk/13871</guid>
<description><![CDATA[ Agents are only as intelligent as the context they can reason over. Today, that context is scattered across data lakes, data warehouses, lakehouses, databases, and streams, and in institutional knowledge that has never been written down. You want to trust the decisions made by your AI agents, but that can&#039;t happen until agents have context. Imagine what becomes possible when we give agents a safe way to access the context they need to deliver trusted decisions. This is why at the AWS Summit New York City, we’re announcing a series of innovations that deliver intelligence for your data and AI agents at scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/17/ml-21188.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 17 Jun 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Context, intelligence, for, your, data, and, agents, scale</media:keywords>
</item>

<item>
<title>New in Amazon Bedrock AgentCore: Build agents with broader knowledge and continuous learning</title>
<link>https://news.jatlink.uk/13858</link>
<guid>https://news.jatlink.uk/13858</guid>
<description><![CDATA[ Today we&#039;re introducing new capabilities on Amazon Bedrock AgentCore, the platform to build, connect, and optimize agents. In this post, we cover how these capabilities close each gap: connecting agents to organizational, web, and paid knowledge; helping teams find and fix what&#039;s going wrong in production; and enforcing controls that scale as agents grow more capable. Together, they help you build more capable agents faster, govern them with controls that scale, and improve them continuously. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/16/21242.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 17 Jun 2026 17:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>New, Amazon, Bedrock, AgentCore:, Build, agents, with, broader, knowledge, and, continuous, learning</media:keywords>
</item>

<item>
<title>Introducing container caching in Amazon SageMaker AI for faster model scaling</title>
<link>https://news.jatlink.uk/13812</link>
<guid>https://news.jatlink.uk/13812</guid>
<description><![CDATA[ Today, we’re excited to announce container image caching for Amazon SageMaker AI inference, the next major advancement in our faster scaling optimization journey. This speeds up end-to-end latency by up to 2x for generative AI models during scale-out events. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/16/ml-21172.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 17 Jun 2026 01:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, container, caching, Amazon, SageMaker, for, faster, model, scaling</media:keywords>
</item>

<item>
<title>Safeguard your agentic AI applications with the Amazon Bedrock Guardrails InvokeGuardrailChecks API</title>
<link>https://news.jatlink.uk/13811</link>
<guid>https://news.jatlink.uk/13811</guid>
<description><![CDATA[ Today, we’re announcing a new API with Amazon Bedrock Guardrails. With this API, you can apply individual safeguards, also referred to as safety checks, at any point in your agentic AI applications without creating guardrail resources. In this post, we walk through how the InvokeGuardrailChecks API works and how to use it to build safe, multi-turn agentic AI applications. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/16/21237-1.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 17 Jun 2026 01:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Safeguard, your, agentic, applications, with, the, Amazon, Bedrock, Guardrails, InvokeGuardrailChecks, API</media:keywords>
</item>

<item>
<title>Parallelize speculative decoding with P&amp;EAGLE on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/13798</link>
<guid>https://news.jatlink.uk/13798</guid>
<description><![CDATA[ This post walks you through how to use P-EAGLE directly within Amazon SageMaker AI. It will demonstrate how to select a compatible model from the SageMaker JumpStart catalog, configure the parallel drafting specifications, and deploy a highly optimized real-time SageMaker AI endpoint to accelerate your generative AI applications. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/16/ml-21171.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 16 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Parallelize, speculative, decoding, with, P-EAGLE, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Introducing Gemma 4 models on Amazon Bedrock</title>
<link>https://news.jatlink.uk/13729</link>
<guid>https://news.jatlink.uk/13729</guid>
<description><![CDATA[ Today, we are announcing the availability of the Gemma 4 family on Amazon Bedrock. Built by Google DeepMind and released under the Apache 2.0 license, Gemma 4 is a family of open-weight models designed with a focus on intelligence-per-parameter across a broad range of deployment scenarios. The family includes three instruction-tuned variants: Gemma 4 31B, Gemma 4 26B-A4B, and Gemma 4 E2B. These cover dense and mixture-of-experts (MoE) architectures, where only a fraction of the model’s parameters activate per request. The variants offer built-in reasoning, native function calling, and multimodal input across text and image. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/15/Gemma4-1.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 16 Jun 2026 01:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Gemma, models, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>AI Agent Failure Detection and Root Cause Analysis with Strands Evals</title>
<link>https://news.jatlink.uk/13717</link>
<guid>https://news.jatlink.uk/13717</guid>
<description><![CDATA[ In this post, we walk you through calling the detector functions to diagnose real agent failures. You learn how to interpret their structured output: categorized failures with confidence scores, causal chains linking root causes to downstream symptoms, and fix recommendations specifying whether a change belongs in your system prompt or tool definitions. You also learn how to integrate detection into your evaluation pipeline for automated diagnosis on every test run. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/15/ml-21169.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 15 Jun 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agent, Failure, Detection, and, Root, Cause, Analysis, with, Strands, Evals</media:keywords>
</item>

<item>
<title>Build context&amp;rich research agents with Deep Agents and Bedrock AgentCore</title>
<link>https://news.jatlink.uk/13701</link>
<guid>https://news.jatlink.uk/13701</guid>
<description><![CDATA[ In this post, you&#039;ll build a competitive research agent that demonstrates this pattern end to end. This walkthrough targets developers building multi-step AI workflows who need isolated execution environments for their agents. In Part 2 of the notebook, you can deploy this same agent to Bedrock AgentCore Runtime using the AgentCore CLI, so it runs as a managed, session-isolated service. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/15/ML-20818-1.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 15 Jun 2026 17:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, context-rich, research, agents, with, Deep, Agents, and, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Building Supercharger: How Rocket Close optimized title operations with agentic AI</title>
<link>https://news.jatlink.uk/13535</link>
<guid>https://news.jatlink.uk/13535</guid>
<description><![CDATA[ In this post, we explore how Rocket Close built a solution using Strands Agents, large language models (LLMs), Amazon Bedrock, Amazon Bedrock Knowledge Bases, and Model Context Protocol (MCP) tools. We cover solution features, the rationale for the technology stack, lessons learned, and the business impact at Rocket Close. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/12/20329.png" length="49398" type="image/jpeg"/>
<pubDate>Sat, 13 Jun 2026 01:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, Supercharger:, How, Rocket, Close, optimized, title, operations, with, agentic</media:keywords>
</item>

<item>
<title>From PDFs to insights: Architecting an intelligent document processing pipeline with AWS generative AI services</title>
<link>https://news.jatlink.uk/13507</link>
<guid>https://news.jatlink.uk/13507</guid>
<description><![CDATA[ This post outlines the development of a cost-effective and scalable intelligent document processing pipeline on AWS, powered by Amazon Bedrock and its features. BDA is a managed service within Amazon Bedrock that automates the extraction of insights from documents. We demonstrate how BDA extracts and analyzes document content, while Strands Agent hosted on Amazon Bedrock AgentCore Runtime coordinate specialized processing tasks, and Amazon Bedrock Knowledge Base enable contextual understanding across multiple documents. By combining these capabilities within a unified architecture, organizations can transform their document processing workflows with minimal development effort. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/12/ml-18003.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 12 Jun 2026 17:00:16 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, PDFs, insights:, Architecting, intelligent, document, processing, pipeline, with, AWS, generative, services</media:keywords>
</item>

<item>
<title>Built from the inside out: How AWS Professional Services became a frontier team first</title>
<link>https://news.jatlink.uk/13508</link>
<guid>https://news.jatlink.uk/13508</guid>
<description><![CDATA[ AWS Professional Services (AWS ProServe) compressed engagement timelines from months to days, not by adding artificial intelligence (AI) tools to an existing process, but by fundamentally rebuilding how we deliver from the inside out. In this post, we share how AWS ProServe became a frontier team, the practices that enabled it, and what your engineering organization can take from our experience. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/11/21052.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 12 Jun 2026 17:00:16 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Built, from, the, inside, out:, How, AWS, Professional, Services, became, frontier, team, first</media:keywords>
</item>

<item>
<title>Build a meeting prep and follow&amp;up assistant with Amazon Quick and Cisco Webex MCP servers</title>
<link>https://news.jatlink.uk/13506</link>
<guid>https://news.jatlink.uk/13506</guid>
<description><![CDATA[ This post shows how to build a custom meeting prep and follow-up assistant using Amazon Quick and Cisco Webex MCP servers. From a single prompt, the agent finds an upcoming Webex meeting, reviews prior meeting summaries and transcripts, and pulls related Vidcast highlights and transcript context. It then searches Webex message threads for unresolved follow-ups and creates a concise prep brief. After the meeting, the same assistant can summarize the discussion and identify action items. It can also find related Vidcast updates and draft a follow-up message for the right Webex space. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/12/ml-21199.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 12 Jun 2026 17:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, meeting, prep, and, follow-up, assistant, with, Amazon, Quick, and, Cisco, Webex, MCP, servers</media:keywords>
</item>

<item>
<title>Extract Data with On&amp;demand and Batch Pipelines Dynamically</title>
<link>https://news.jatlink.uk/13434</link>
<guid>https://news.jatlink.uk/13434</guid>
<description><![CDATA[ This post demonstrates an intelligent document processing pipeline that consists of both on-demand inference and batch inference options on Amazon Bedrock to enable the flexibility on the document processing time and cost. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/02/ML-18264.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 11 Jun 2026 21:00:19 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Extract, Data, with, On-demand, and, Batch, Pipelines, Dynamically</media:keywords>
</item>

<item>
<title>Evaluate AI agents systematically with Agent&amp;EvalKit</title>
<link>https://news.jatlink.uk/13417</link>
<guid>https://news.jatlink.uk/13417</guid>
<description><![CDATA[ Agent-EvalKit is an open-source toolkit (Apache 2.0) that makes this evaluation infrastructure available by integrating with AI coding assistants, including Claude Code, Kiro CLI, and Kilo Code. This post walks through how Agent-EvalKit works across its six evaluation phases, using a travel research agent built with the Strands Agents SDK and Amazon Bedrock as a running example. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20590/EvalKit-Demo-v2.mp4" length="49398" type="image/jpeg"/>
<pubDate>Thu, 11 Jun 2026 17:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evaluate, agents, systematically, with, Agent-EvalKit</media:keywords>
</item>

<item>
<title>Spot trends faster, sort smarter: Unlocking Sparklines and Custom Sort in Amazon Quick</title>
<link>https://news.jatlink.uk/13418</link>
<guid>https://news.jatlink.uk/13418</guid>
<description><![CDATA[ Today, we’re excited to announce two new capabilities that make Quick Sight dashboards even more expressive and business-aligned: sparklines and custom sort for controls. In this post, we walk through both features, what they are, when to use them, and how to configure them, with real-world scenarios that bring them together in a practical, decision-ready dashboard. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20928/1.mp4" length="49398" type="image/jpeg"/>
<pubDate>Thu, 11 Jun 2026 17:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Spot, trends, faster, sort, smarter:, Unlocking, Sparklines, and, Custom, Sort, Amazon, Quick</media:keywords>
</item>

<item>
<title>Optimize blueprint extraction accuracy in Amazon Bedrock Data Automation</title>
<link>https://news.jatlink.uk/13419</link>
<guid>https://news.jatlink.uk/13419</guid>
<description><![CDATA[ Blueprint instruction optimization is a BDA feature that automatically refines your extraction instructions to address this challenge directly. You provide three to ten example documents with expected values, and BDA refines your blueprint instructions to improve accuracy in minutes, not weeks. No separate model fine-tuning is required. By the end of this post, you can optimize your blueprints to improve accuracy, run the optimization workflow through the Amazon Bedrock console or the API, and apply best practices for selecting examples and ground truth. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/04/21032.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 11 Jun 2026 17:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Optimize, blueprint, extraction, accuracy, Amazon, Bedrock, Data, Automation</media:keywords>
</item>

<item>
<title>How frontier teams are reinventing AI&amp;native development</title>
<link>https://news.jatlink.uk/13373</link>
<guid>https://news.jatlink.uk/13373</guid>
<description><![CDATA[ Frontier teams are not just using AI to code faster. They’re redesigning how software gets built. The result is 4.5x productivity gains, in some cases more than 10x. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/10/Frontierteams.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 11 Jun 2026 05:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, frontier, teams, are, reinventing, AI-native, development</media:keywords>
</item>

<item>
<title>Stop hand&amp;tuning kernels: How Neuron Agentic Development accelerates AWS Trainium optimizations</title>
<link>https://news.jatlink.uk/13328</link>
<guid>https://news.jatlink.uk/13328</guid>
<description><![CDATA[ Today, we’re announcing the Neuron Agentic Development capabilities: a collection of AI agents and skills that make this possible for developers building on AWS Trainium and AWS Inferentia. In this post, we explain how the Neuron Agentic Development capabilities accelerate the kernel development workflow. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/10/ml-20937.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 10 Jun 2026 17:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Stop, hand-tuning, kernels:, How, Neuron, Agentic, Development, accelerates, AWS, Trainium, optimizations</media:keywords>
</item>

<item>
<title>Build an AI&amp;Powered Equipment Repair Assistant Using Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/13329</link>
<guid>https://news.jatlink.uk/13329</guid>
<description><![CDATA[ In this post, you build an AI-powered equipment repair assistant using Amazon Bedrock AgentCore that helps farmers and field technicians diagnose equipment problems, identify required parts, and access manufacturer-approved repair procedures through natural language. The solution uses AgentCore Runtime with the Strands Agents SDK, Amazon Nova 2 Lite as the foundation model, Amazon Bedrock Knowledge Base for retrieval-augmented generation (RAG), and AgentCore Memory for conversation persistence. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/18699.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 10 Jun 2026 17:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, AI-Powered, Equipment, Repair, Assistant, Using, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Scale Robot Reinforcement Learning with NVIDIA Isaac Lab on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/13273</link>
<guid>https://news.jatlink.uk/13273</guid>
<description><![CDATA[ In this post, we show how to train robot policies for the Unitree H1 humanoid with NVIDIA Isaac Lab on Amazon SageMaker AI across two compute options: Amazon SageMaker HyperPod and Amazon SageMaker Training Jobs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/09/ML-20813.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 10 Jun 2026 01:00:16 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scale, Robot, Reinforcement, Learning, with, NVIDIA, Isaac, Lab, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Hands&amp;free first notice of loss: Using Strands Agents and Amazon Bedrock AgentCore Browser Tool for intelligent claims intake</title>
<link>https://news.jatlink.uk/13258</link>
<guid>https://news.jatlink.uk/13258</guid>
<description><![CDATA[ In this post, we demonstrate how a hands-free FNOL intake system combines agents built with the Strands Agents SDK for domain reasoning with Amazon Bedrock AgentCore Browser Tool for live portal interaction. This approach preserves human expertise while removing repetitive screen work. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/09/ml-19303.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 09 Jun 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Hands-free, first, notice, loss:, Using, Strands, Agents, and, Amazon, Bedrock, AgentCore, Browser, Tool, for, intelligent, claims, intake</media:keywords>
</item>

<item>
<title>Build an agentic incident triage assistant with Amazon Quick and New Relic</title>
<link>https://news.jatlink.uk/13259</link>
<guid>https://news.jatlink.uk/13259</guid>
<description><![CDATA[ This post shows engineering teams how to apply that principle to one of the most time-sensitive workflows in engineering: incident triage. You will build a custom incident triage assistant agent using Amazon Quick that orchestrates a response with the New Relic Model Context Protocol (MCP) Server and Asana through native integrations. From a single prompt, the Amazon Quick agent investigates the incident, assembles a root cause analysis (RCA) brief with evidence links, and creates a tracked Asana task ready for handoff. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/04/ML-20579-1-1146x630.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 09 Jun 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, agentic, incident, triage, assistant, with, Amazon, Quick, and, New, Relic</media:keywords>
</item>

<item>
<title>End&amp;to&amp;end encrypted ML inference with Amazon SageMaker AI and FHE</title>
<link>https://news.jatlink.uk/13184</link>
<guid>https://news.jatlink.uk/13184</guid>
<description><![CDATA[ This blog has previously discussed FHE for ML inference in the post Enable fully homomorphic encryption with Amazon SageMaker endpoints for secure, real-time inferencing, but this post goes a little further. That previous post showed how to implement FHE-based inference &#039;from scratch&#039; by hand-crafting a linear-regression algorithm using a low-level library called SEAL. Instead, this post shows a much more flexible and higher-level approach based on concrete-ml, a high-level library built specifically for FHE-based inference. It supports several common types of models &#039;out of the box&#039; and is even API compatible with the well-known ML library scikit-learn. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/ML-18990.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 08 Jun 2026 21:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>End-to-end, encrypted, inference, with, Amazon, SageMaker, and, FHE</media:keywords>
</item>

<item>
<title>Amazon Quick ARNs: Cross&amp;account migration and namespace permissions</title>
<link>https://news.jatlink.uk/13185</link>
<guid>https://news.jatlink.uk/13185</guid>
<description><![CDATA[ In this post, we cover the structure of Amazon Quick ARNs and provide a practical mental model for working with them. By the end, you can look at an ARN and immediately understand what it means for your migration strategy, diagnose permission issues faster, and design multi-tenant architectures with confidence. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/08/ml-20693.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 08 Jun 2026 21:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Quick, ARNs:, Cross-account, migration, and, namespace, permissions</media:keywords>
</item>

<item>
<title>Better decisions at scale: How mathematical optimization delivers where intuition fails</title>
<link>https://news.jatlink.uk/13183</link>
<guid>https://news.jatlink.uk/13183</guid>
<description><![CDATA[ In this post, we introduce mathematical optimization, explain how it fits within the broader AI landscape, and showcase real-world success stories where the Innovation Center has partnered with customers to deliver concrete results. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/08/ml-21077.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 08 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Better, decisions, scale:, How, mathematical, optimization, delivers, where, intuition, fails</media:keywords>
</item>

<item>
<title>Unlocking AI flexibility in Europe: A guide to cross&amp;region inference for EU data processing and model access</title>
<link>https://news.jatlink.uk/13181</link>
<guid>https://news.jatlink.uk/13181</guid>
<description><![CDATA[ With access to the latest generative AI models and high-performance accelerated compute in high global demand, AWS customers need tools to take advantage of model availability and capacity across multiple AWS Regions, while still meeting their security and privacy requirements. cross-Region Inference (CRIS) on Amazon Bedrock meets these needs by automatically routing requests across multiple […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/ML-20090.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 08 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Unlocking, flexibility, Europe:, guide, cross-region, inference, for, data, processing, and, model, access</media:keywords>
</item>

<item>
<title>It’s safe to close your laptop now: Hosting coding agents on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/13182</link>
<guid>https://news.jatlink.uk/13182</guid>
<description><![CDATA[ Amazon Bedrock AgentCore Runtime gives each agent session its own isolated microVM with a persistent workspace, secure tool access through Gateway, and built-in observability—so you can run Claude Code, Codex, Kiro, and Cursor in parallel without sharing secrets, ports, or filesystems. Close the lid, go to dinner, and pick up where you left off tomorrow. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/20817.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 08 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>It’s, safe, close, your, laptop, now:, Hosting, coding, agents, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Evaluate your Amazon Nova Sonic voice agent at scale, no microphone required</title>
<link>https://news.jatlink.uk/13167</link>
<guid>https://news.jatlink.uk/13167</guid>
<description><![CDATA[ In this post, we walk you through the Nova Sonic Test Harness, an open source framework that we built to solve both problems. It serves as a rapid iteration tool for tuning system prompts and tool configurations (run a conversation, see results, adjust, repeat) and as a comprehensive evaluation framework for validating voice agent quality at scale. It runs complete multi-turn conversations with Amazon Nova Sonic automatically, evaluates them using LLM-as-judge techniques, and can even detect cases where the model’s audio output doesn’t match its text output (audio hallucinations). No microphone required. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/08/ml-21086.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 08 Jun 2026 17:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evaluate, your, Amazon, Nova, Sonic, voice, agent, scale, microphone, required</media:keywords>
</item>

<item>
<title>NVIDIA Nemotron 3 Ultra now available on Amazon SageMaker JumpStart</title>
<link>https://news.jatlink.uk/12873</link>
<guid>https://news.jatlink.uk/12873</guid>
<description><![CDATA[ Deploy NVIDIA Nemotron 3 Ultra on Amazon SageMaker JumpStart. Get 5x faster inference and 30% lower cost for agentic AI workloads with this frontier reasoning model. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/21170.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 04 Jun 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>NVIDIA, Nemotron, Ultra, now, available, Amazon, SageMaker, JumpStart</media:keywords>
</item>

<item>
<title>How to build self&amp;driving AI operations on Amazon Bedrock at scale</title>
<link>https://news.jatlink.uk/12801</link>
<guid>https://news.jatlink.uk/12801</guid>
<description><![CDATA[ In this post, we introduce Amazon Bedrock Ops Alert, a three-layer automated monitoring solution that proactively detects operational issues, dynamically adjusts alarm thresholds, classifies alarms by category, automatically creates context-aware support cases, helps prevent duplicate cases when an unresolved case of the same alarm category is already active, and delivers contextualized notifications to AI SRE teams. We walk through the solution architecture and how you can deploy it in your own environment. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/20534.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 04 Jun 2026 01:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, build, self-driving, operations, Amazon, Bedrock, scale</media:keywords>
</item>

<item>
<title>Fundamental’s Large Tabular Model NEXUS is now available on Amazon SageMaker JumpStart</title>
<link>https://news.jatlink.uk/12784</link>
<guid>https://news.jatlink.uk/12784</guid>
<description><![CDATA[ In this post, we show you how to get started with NEXUS on Amazon SageMaker JumpStart, walk through the deployment process, and demonstrate how to run predictions against your enterprise datasets. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/nexus.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 03 Jun 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Fundamental’s, Large, Tabular, Model, NEXUS, now, available, Amazon, SageMaker, JumpStart</media:keywords>
</item>

<item>
<title>Reducing container cold start times using SOCI index on DLAMI and DLC</title>
<link>https://news.jatlink.uk/12785</link>
<guid>https://news.jatlink.uk/12785</guid>
<description><![CDATA[ In this post, we look at how to use SOCI on publicly available Deep Learning AMIs and Containers, when to use the various SOCI modes provided by the tool, and how to quickly and efficiently use this tool in your workloads today. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/ML-20939.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 03 Jun 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reducing, container, cold, start, times, using, SOCI, index, DLAMI, and, DLC</media:keywords>
</item>

<item>
<title>Improve your agent’s tool&amp;calling accuracy with SFT and DPO on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/12766</link>
<guid>https://news.jatlink.uk/12766</guid>
<description><![CDATA[ In this post, you learn how to use Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) together to improve the tool-calling accuracy of a small language model (SLM). The example uses Amazon SageMaker AI training jobs, so you can focus on training code instead of managing your own training infrastructure. You also learn how to evaluate tool-calling accuracy and compare a base model to several fine-tuned variants, so you can make data-driven decisions about model quality. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/03/20404.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 03 Jun 2026 17:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Improve, your, agent’s, tool-calling, accuracy, with, SFT, and, DPO, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>The art and science of hyperparameter optimization on Amazon Nova Forge</title>
<link>https://news.jatlink.uk/12691</link>
<guid>https://news.jatlink.uk/12691</guid>
<description><![CDATA[ Fine-tuning for domain-specific tasks means improving performance in one area without degrading the model’s general capabilities, and getting that balance right is harder than it looks. This post walks through how to navigate that balance, from selecting the right customization strategy for your data and task, to configuring the training parameters that most influence outcomes, like learning rate, batch size, and checkpointing. We also cover the common mistakes that lead to wasted training runs and how to catch them early, so you can improve domain performance without degrading general capabilities or burning through compute on avoidable failures. By the end, you will know how to improve domain performance without degrading general capabilities and how to avoid the expensive failures that come from getting the balance wrong. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/02/20384.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 02 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>The, art, and, science, hyperparameter, optimization, Amazon, Nova, Forge</media:keywords>
</item>

<item>
<title>Object detection with Amazon Nova 2 Lite</title>
<link>https://news.jatlink.uk/12692</link>
<guid>https://news.jatlink.uk/12692</guid>
<description><![CDATA[ In this post, we&#039;ll walk through implementing object detection with Amazon Nova 2 Lite. You&#039;ll learn how to deploy an object detection application using Amazon Bedrock, AWS Lambda, and Amazon API Gateway. You&#039;ll also learn how to craft effective prompts, process structured JSON output, and visualize results. We explore practical applications across manufacturing, agriculture, and logistics. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/02/200421.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 02 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Object, detection, with, Amazon, Nova, Lite</media:keywords>
</item>

<item>
<title>How Baz improved its AI Agent Code Review accuracy using Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12678</link>
<guid>https://news.jatlink.uk/12678</guid>
<description><![CDATA[ This post walks through how Baz built their Spec Review agent using Amazon Bedrock and Amazon Bedrock AgentCore. We&#039;ll cover the architecture decisions, implementation details, and the business outcomes they achieved by leveraging these AWS services to automate their code review process ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/02/19914.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 02 Jun 2026 17:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Baz, improved, its, Agent, Code, Review, accuracy, using, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Building a secure auth code flow setup using AgentCore Gateway with MCP clients</title>
<link>https://news.jatlink.uk/12632</link>
<guid>https://news.jatlink.uk/12632</guid>
<description><![CDATA[ This post demonstrates how to implement Open Authorization (OAuth) Code flow as an inbound authorization mechanism for MCP servers hosted on Amazon Bedrock AgentCore Gateway. By the end of this guide, you will have a production-ready setup where each AI assistant request is authenticated with a valid user identity token issued from your organization’s identity provider. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/ML-20412-1.jpg" length="49398" type="image/jpeg"/>
<pubDate>Tue, 02 Jun 2026 05:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, secure, auth, code, flow, setup, using, AgentCore, Gateway, with, MCP, clients</media:keywords>
</item>

<item>
<title>OpenAI models and Codex on Amazon Bedrock are now generally available</title>
<link>https://news.jatlink.uk/12616</link>
<guid>https://news.jatlink.uk/12616</guid>
<description><![CDATA[ GPT-5.5, GPT-5.4, and Codex are now generally available on Amazon Bedrock. Deploy them in production applications and agents today, on Bedrock’s high performance inference engine.  ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/21096.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 02 Jun 2026 01:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>OpenAI, models, and, Codex, Amazon, Bedrock, are, now, generally, available</media:keywords>
</item>

<item>
<title>Transforming rare cancer research with Amazon Quick: Integrating biomedical databases for breakthrough discoveries</title>
<link>https://news.jatlink.uk/12615</link>
<guid>https://news.jatlink.uk/12615</guid>
<description><![CDATA[ In this post, we walk through how to use Amazon Quick Research to integrate biomedical data sources for rare cancer research. The walkthrough uses pediatric sarcoma as the research domain and draws on publicly available datasets from PubMed and other open biomedical repositories. It covers the end-to-end workflow: defining a research objective, configuring data sources, reviewing the AI-generated research plan, running the investigation, and iterating on results using the revision and versioning system. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-20129/Rare Cancer Research Demo .mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 02 Jun 2026 01:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Transforming, rare, cancer, research, with, Amazon, Quick:, Integrating, biomedical, databases, for, breakthrough, discoveries</media:keywords>
</item>

<item>
<title>Reference your own AWS Secrets Manager secrets in Amazon Bedrock AgentCore Identity</title>
<link>https://news.jatlink.uk/12614</link>
<guid>https://news.jatlink.uk/12614</guid>
<description><![CDATA[ Today, we’re excited to announce the ability to reference a secret in AWS Secrets Manager for AgentCore Identity, so you can reference your own preconfigured secret from Secrets Manager and retain full control over how it is managed. With this ability, you can extend your organization’s existing secrets governance processes to AgentCore. You can provide an existing, preconfigured AWS Secrets Manager secret to use with your credential provider resources. You retain full control over its encryption configuration, rotation, replication, tags, and resource policies, just as you would manage other secrets in Secrets Manager. You can also choose a secret from another AWS account within the same AWS Region, though cross-Region secret sharing isn’t supported. This also supports secrets brought in through AWS Secrets Manager external connectors, enabling integration with third-party secret managers. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/21022.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 02 Jun 2026 01:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reference, your, own, AWS, Secrets, Manager, secrets, Amazon, Bedrock, AgentCore, Identity</media:keywords>
</item>

<item>
<title>AgentOps: Operationalize agentic AI at scale with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12596</link>
<guid>https://news.jatlink.uk/12596</guid>
<description><![CDATA[ When you build agentic AI solutions, you face unique operational challenges. Agents make unpredictable decisions, costs spiral unexpectedly, and debugging non-deterministic failures seems impossible. Agentic AI applications don&#039;t just execute predetermined workflows. They reason, adapt, and make autonomous decisions, and DevOps practices need to be adapted. That&#039;s where AgentOps comes in, the operational discipline for deploying, managing, and continuously improving AI agents in production. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/19465.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 01 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AgentOps:, Operationalize, agentic, scale, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Accelerate LLM model loading and increase context windows with GPUDirect on Amazon FSx for Lustre and TurboQuant</title>
<link>https://news.jatlink.uk/12597</link>
<guid>https://news.jatlink.uk/12597</guid>
<description><![CDATA[ If you’re iterating on deploying large language models (LLMs) on AWS GPU instances, you’ve probably noticed the larger the model to be loaded into GPU High Bandwidth Memory (HBM), the longer the painful wait until the GPUs are ready for inference. As models grow to hundreds of billions of parameters and GPU environments grow ever […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/20/ML-20909.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 01 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerate, LLM, model, loading, and, increase, context, windows, with, GPUDirect, Amazon, FSx, for, Lustre, and, TurboQuant</media:keywords>
</item>

<item>
<title>Amazon Quick integration with time&amp;series databases for market intelligence using MCP</title>
<link>https://news.jatlink.uk/12598</link>
<guid>https://news.jatlink.uk/12598</guid>
<description><![CDATA[ In this post, we walk through a practical implementation using KDB-X MCP server integration with Amazon Quick, demonstrating how traders and analysts can ask questions using conversational language and receive actionable insights from datasets. You can apply this same integration pattern across various domains, from financial market analysis to IoT sensor monitoring to DevOps performance dashboards, where you need to simplify access to time series insights. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/20251.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 01 Jun 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Quick, integration, with, time-series, databases, for, market, intelligence, using, MCP</media:keywords>
</item>

<item>
<title>Enable safe agentic payments with built&amp;in guardrails using Amazon Bedrock AgentCore payments</title>
<link>https://news.jatlink.uk/12595</link>
<guid>https://news.jatlink.uk/12595</guid>
<description><![CDATA[ In this post, we address several key risks that surface when designing an agentic payment system, and how to address them with the capabilities of AgentCore payments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/21076.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 01 Jun 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Enable, safe, agentic, payments, with, built-in, guardrails, using, Amazon, Bedrock, AgentCore, payments</media:keywords>
</item>

<item>
<title>Extending MCP support for Amazon Bedrock AgentCore Gateway</title>
<link>https://news.jatlink.uk/12593</link>
<guid>https://news.jatlink.uk/12593</guid>
<description><![CDATA[ While deploying Model Context Protocol (MCP) servers in production, enterprises need fine-grained access control across servers, observability into which teams use which tools, security guarantees against data exfiltration, and centralized credential management, all at scale. Amazon Bedrock AgentCore Gateway sits between MCP servers and the clients that consume them, centralizing credential management, observability, and secure […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/20987.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 01 Jun 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Extending, MCP, support, for, Amazon, Bedrock, AgentCore, Gateway</media:keywords>
</item>

<item>
<title>Secure AI agents with Policy and Lambda interceptors in Amazon Bedrock AgentCore gateway</title>
<link>https://news.jatlink.uk/12594</link>
<guid>https://news.jatlink.uk/12594</guid>
<description><![CDATA[ In this post, we use a lakehouse data agent to demonstrate how you can use Policy for deterministic access control and Lambda interceptors for dynamic validation. We then show how to combine Lambda interceptors and Policy to implement a geography-based access control which requires both dynamic validation and deterministic access control. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/06/01/20712.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 01 Jun 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Secure, agents, with, Policy, and, Lambda, interceptors, Amazon, Bedrock, AgentCore, gateway</media:keywords>
</item>

<item>
<title>Comprehensive observability for Amazon SageMaker AI LLM inference: From GPU utilization to LLM quality</title>
<link>https://news.jatlink.uk/12381</link>
<guid>https://news.jatlink.uk/12381</guid>
<description><![CDATA[ This post demonstrates a comprehensive observability solution using Amazon Managed Grafana dashboards that provides a holistic view of both quality and quantity for LLMs served on Amazon SageMaker AI endpoints with inference components. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/29/21002.png" length="49398" type="image/jpeg"/>
<pubDate>Sat, 30 May 2026 01:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Comprehensive, observability, for, Amazon, SageMaker, LLM, inference:, From, GPU, utilization, LLM, quality</media:keywords>
</item>

<item>
<title>Streamline external access to Amazon SageMaker MLflow using a REST API proxy</title>
<link>https://news.jatlink.uk/12300</link>
<guid>https://news.jatlink.uk/12300</guid>
<description><![CDATA[ In this post, we demonstrate how to build a secure Flask-based MLflow proxy service that provides HTTPS access to Amazon SageMaker MLflow without requiring the MLflow SDK. This solution is for organizations undergoing cloud transformation who want to preserve their existing ML workflows while adopting cloud-native services. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/28/19491.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 29 May 2026 01:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Streamline, external, access, Amazon, SageMaker, MLflow, using, REST, API, proxy</media:keywords>
</item>

<item>
<title>Evaluating Deep Agents using LangSmith on AWS</title>
<link>https://news.jatlink.uk/12301</link>
<guid>https://news.jatlink.uk/12301</guid>
<description><![CDATA[ This post combines learnings from LangChain’s work on evaluating deep agents and Anthropic’s guide to demystifying evals for AI agents into a practical guide. In this post, you will learn how to: 1) apply five evaluation patterns for deep agents, 2) build offline evaluations using pytest and LangSmith, and 3) configure online monitoring for production. The walkthrough uses a text-to-SQL deep agent with Amazon Bedrock for the full development to production lifecycle. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/28/20403.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 29 May 2026 01:00:17 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Evaluating, Deep, Agents, using, LangSmith, AWS</media:keywords>
</item>

<item>
<title>Build a custom portal with embedded Amazon SageMaker AI MLflow Apps</title>
<link>https://news.jatlink.uk/12299</link>
<guid>https://news.jatlink.uk/12299</guid>
<description><![CDATA[ In this post, you learn how to build a custom portal with embedded SageMaker AI MLflow Apps UI. You walk through the architecture pattern behind a React front end paired with a Flask reverse proxy that handles AWS Signature Version 4 (SigV4) authentication, deploy the entire stack through the AWS Cloud Development Kit (AWS CDK), validate the deployment, and review security considerations and cleanup procedures. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/28/20734.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 29 May 2026 01:00:16 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, custom, portal, with, embedded, Amazon, SageMaker, MLflow, Apps</media:keywords>
</item>

<item>
<title>Training Azerbaijani language models on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/12298</link>
<guid>https://news.jatlink.uk/12298</guid>
<description><![CDATA[ Azercell Telecom LLC, Azerbaijan&#039;s leading telecommunications provider, wanted to build an Azerbaijani large language model (LLM) on Amazon SageMaker AI for telecom use cases and a customer-facing chatbot. The challenge: adapting foundation models (FMs) to a morphologically rich language with limited training data and no existing blueprint for efficient LLM training in Azerbaijani. In a six-week collaboration, Azercell worked with the AWS Generative AI Innovation Center to establish a production-ready framework on Amazon SageMaker AI. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/28/20305.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 29 May 2026 01:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Training, Azerbaijani, language, models, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Claude Opus 4.8 is now available on AWS</title>
<link>https://news.jatlink.uk/12281</link>
<guid>https://news.jatlink.uk/12281</guid>
<description><![CDATA[ This post covers Opus 4.8&#039;s improvements and practical guidance for AI engineers integrating the model into agentic systems and production inference workloads on Amazon Bedrock. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/28/21036.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 28 May 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Claude, Opus, 4.8, now, available, AWS</media:keywords>
</item>

<item>
<title>Build a test suite that grows with your agent with dataset management in Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12280</link>
<guid>https://news.jatlink.uk/12280</guid>
<description><![CDATA[ Agent evaluation is most powerful when you combine fast-moving online signals with stable offline baselines. To understand whether your agent is truly improving over time, you need a fixed benchmark alongside your changing real-world traffic. Managing test cases for evaluation baselines as a dataset in Amazon Bedrock AgentCore brings the discipline of versioned test fixtures […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/28/21133.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 28 May 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, test, suite, that, grows, with, your, agent, with, dataset, management, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Automate AML alert triage with Amazon Quick and Snowflake Cortex AI</title>
<link>https://news.jatlink.uk/12282</link>
<guid>https://news.jatlink.uk/12282</guid>
<description><![CDATA[ This post demonstrates that integration in action by automating one of the most labor-intensive workflows in financial services: anti-money laundering (AML) alert triage. You will build a triage workflow using Amazon Quick Flows and Snowflake Cortex, connected through the Amazon Quick Model Context Protocol (MCP) integration. In our testing environment, automated workflows built using Amazon Quick reduced alert investigation time from 30-90 minutes to under 5 minutes. Actual results may vary based on alert complexity and data volume. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/28/20391.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 28 May 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, AML, alert, triage, with, Amazon, Quick, and, Snowflake, Cortex</media:keywords>
</item>

<item>
<title>Building AI agents for business support using Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12206</link>
<guid>https://news.jatlink.uk/12206</guid>
<description><![CDATA[ In this post, we share how the AWS Generative AI Innovation Center (GenAIIC) collaborated with Works Human Intelligence (WHI) to build two AI agents using Amazon Bedrock AgentCore. We discuss the challenges encountered and the solutions that reduced costs by up to 97% while improving operational efficiency. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/27/20255.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 28 May 2026 01:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, agents, for, business, support, using, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>From data overload to actionable insights: How Verizon Connect scaled agentic AI to 100,000 users</title>
<link>https://news.jatlink.uk/12207</link>
<guid>https://news.jatlink.uk/12207</guid>
<description><![CDATA[ In this post, we show you how Verizon Connect built and scaled an agentic AI solution to transform overwhelming fleet data into clear, actionable insights for 100,000 users daily. We walk you through the architectural decisions, implementation challenges, and measurable results that can guide your own data-to-insights transformation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/27/20194.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 28 May 2026 01:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, data, overload, actionable, insights:, How, Verizon, Connect, scaled, agentic, 100, 000, users</media:keywords>
</item>

<item>
<title>Process financial documents using Amazon Bedrock Data Automation</title>
<link>https://news.jatlink.uk/12205</link>
<guid>https://news.jatlink.uk/12205</guid>
<description><![CDATA[ In this post, we explore how Amazon Bedrock Data Automation can accurately extract information from four common types of financial documents: bank statements, W-2 forms, 1099-B tax forms, and vendor contracts. We highlight the complexity in the documents, detail the custom extraction created in Amazon Bedrock Data Automation, and describe the outcomes of the extraction process. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/27/19347.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 28 May 2026 01:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Process, financial, documents, using, Amazon, Bedrock, Data, Automation</media:keywords>
</item>

<item>
<title>Powering agentic AI sales strategy with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12190</link>
<guid>https://news.jatlink.uk/12190</guid>
<description><![CDATA[ As agent adoption scaled, we saw a common pattern emerge across enterprises, including our own sales organization: specialized agents deliver value, but without orchestration, users carry the cognitive load of choosing between them. At AWS Sales, this meant more than 20 domain-specific agents deployed across the global organization, with representatives context-switching between systems instead of […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/27/20754.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 27 May 2026 21:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Powering, agentic, sales, strategy, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>How AWS SMGS uses an AI&amp;powered conversational assistant to transform business management with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12189</link>
<guid>https://news.jatlink.uk/12189</guid>
<description><![CDATA[ In this post, we share how we built NarrateAI using Amazon Bedrock AgentCore to deliver business intelligence at scale for the AWS SMGS (Sales, Marketing and Global Services) organization. You will learn about: the two-layer architecture that separates batch processing from real-time interaction, the specialized AI agents that power intelligent routing and validation, key engineering patterns for production deployment, and how to build similar solutions with AWS services. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/27/20454.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 27 May 2026 21:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, AWS, SMGS, uses, AI-powered, conversational, assistant, transform, business, management, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>AgentWatch: Proactive AWS monitoring with ambient agents</title>
<link>https://news.jatlink.uk/12102</link>
<guid>https://news.jatlink.uk/12102</guid>
<description><![CDATA[ In this post, we demonstrate the capabilities of AgentWatch through practical implementation. You will see how the solution performs infrastructure checks every 15 minutes, summarizing CloudWatch metrics, logs, and alarms across multiple AWS accounts. The agent delivers actionable reports directly to Slack and responds to natural language queries about your infrastructure state. Throughout, we explore three human-in-the-loop patterns that maintain appropriate oversight while maximizing automation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/20132.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 26 May 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AgentWatch:, Proactive, AWS, monitoring, with, ambient, agents</media:keywords>
</item>

<item>
<title>From idea to AI app: Creating intelligent research assistants with Strands</title>
<link>https://news.jatlink.uk/12103</link>
<guid>https://news.jatlink.uk/12103</guid>
<description><![CDATA[ Building an AI app shouldn’t require a PhD in machine learning (ML) or months of wrestling with complex architectures. Yet that’s exactly what happens when you try to orchestrate multiple API calls, manage conversation state, and create agents that can reason on their own. I’ve seen straightforward AI ideas balloon into sprawling projects that demand […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/ML-19684.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 26 May 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, idea, app:, Creating, intelligent, research, assistants, with, Strands</media:keywords>
</item>

<item>
<title>Build an enterprise observability solution for Amazon Quick</title>
<link>https://news.jatlink.uk/12104</link>
<guid>https://news.jatlink.uk/12104</guid>
<description><![CDATA[ When hundreds to thousands of users are onboarded to an enterprise AI platform, business leaders and platform owners need visibility into who is using the platform, whether users are satisfied with the answers they receive, and which capabilities are driving the most engagement. Without a centralized observability solution, this data is scattered across multiple AWS […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/20929.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 26 May 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, enterprise, observability, solution, for, Amazon, Quick</media:keywords>
</item>

<item>
<title>Technical deep dive: AgentCore payments and innovation in agentic commerce</title>
<link>https://news.jatlink.uk/12099</link>
<guid>https://news.jatlink.uk/12099</guid>
<description><![CDATA[ Amazon Bedrock AgentCore payments is now available in preview, it provides instant payments to paid external services with no manual billing setup per provider, stablecoin support for cost-effective microtransactions that make sub-cent transactions economically viable, and configurable spending guardrails that give you fine-grained control over agent budgets and transaction limits. In this post, we walk you through a technical deep dive of AgentCore payments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/21056_2.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 26 May 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Technical, deep, dive:, AgentCore, payments, and, innovation, agentic, commerce</media:keywords>
</item>

<item>
<title>Build highly scalable serverless LangGraph multi&amp;agent systems in AWS with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12100</link>
<guid>https://news.jatlink.uk/12100</guid>
<description><![CDATA[ In this post, we provide a solution to build highly scalable, serverless multi-agent generative AI systems on AWS using LangGraph Agents as orchestrators integrated with Amazon Bedrock AgentCore Memory and Amazon Bedrock AgentCore Observability. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/20165.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 26 May 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, highly, scalable, serverless, LangGraph, multi-agent, systems, AWS, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Build high&amp;performance generative AI systems with Strands Agents, NVIDIA NIM, and Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/12101</link>
<guid>https://news.jatlink.uk/12101</guid>
<description><![CDATA[ In this post you&#039;ll learn how to build a multi-agent campaign review system that demonstrates parallel reasoning, context persistence, and traceable execution paths using an integrated architecture that combines NVIDIA NIM for GPU-accelerated inference. Amazon Bedrock AgentCore provides managed runtime, shared memory and built-in observability and Strands Agents provide serverless multi-agent orchestration. This approach supports performance, scalability, and operational insight in production environments. While the example focuses on marketing content review, the same pattern applies to digital assistants, review automation, and retrieval-augmented generation pipelines. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/26/20164.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 26 May 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, high-performance, generative, systems, with, Strands, Agents, NVIDIA, NIM, and, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Transforming professional work: How Amazon Quick turns document creation from hours into minutes</title>
<link>https://news.jatlink.uk/12087</link>
<guid>https://news.jatlink.uk/12087</guid>
<description><![CDATA[ In this post, we explore how the Amazon Quick document and visualization creation capabilities work, what you can build with them, and how professionals across roles are using them to reclaim hours of their workweek. From technical execution to strategic judgment Most professional roles carry an unspoken assumption that a significant portion of your time […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/20925.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 26 May 2026 17:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Transforming, professional, work:, How, Amazon, Quick, turns, document, creation, from, hours, into, minutes</media:keywords>
</item>

<item>
<title>Amazon Nova Act is now HIPAA eligible</title>
<link>https://news.jatlink.uk/11753</link>
<guid>https://news.jatlink.uk/11753</guid>
<description><![CDATA[ In this post, you will learn what Nova Act offers, how HIPAA eligibility applies to agentic AI, and how to get started. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/20736.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 22 May 2026 01:00:15 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Nova, Act, now, HIPAA, eligible</media:keywords>
</item>

<item>
<title>Build an AI&amp;powered recruitment assistant using Amazon Bedrock</title>
<link>https://news.jatlink.uk/11738</link>
<guid>https://news.jatlink.uk/11738</guid>
<description><![CDATA[ In this post, we demonstrate how to build an AI-powered recruitment assistant using Amazon Bedrock that brings efficiencies to candidate evaluation, generates personalized interview questions, and provides data-driven insights for human hiring decisions. This post presents a reference architecture for learning purposes — not a production-ready solution. Amazon Bedrock and the AWS services used here are general-purpose tools that customers can combine to support a wide variety of use cases, including recruitment workflows. The architecture demonstrates one possible approach; customers should adapt it to their specific requirements. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/18419.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 21:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, AI-powered, recruitment, assistant, using, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Building multi&amp;tenant agents with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/11735</link>
<guid>https://news.jatlink.uk/11735</guid>
<description><![CDATA[ This post explores design considerations for architecting multi-tenant agentic applications and the framework needed to address SaaS architecture challenges with Amazon Bedrock AgentCore. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/Ml-20532-image-1-1-1101x630.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, multi-tenant, agents, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Build AI agents for business intelligence with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/11737</link>
<guid>https://news.jatlink.uk/11737</guid>
<description><![CDATA[ In this post, we show you how OPLOG developed three AI agents using the Strands Agents SDK, deployed them to Amazon Bedrock AgentCore, and integrated Amazon Bedrock with Anthropic’s Claude Sonnet and Amazon Bedrock Knowledge Bases for Retrieval Augmented Generation (RAG). ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/20112.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, agents, for, business, intelligence, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Intelligent radiology workflow optimization with AI agents</title>
<link>https://news.jatlink.uk/11733</link>
<guid>https://news.jatlink.uk/11733</guid>
<description><![CDATA[ Many healthcare organizations report that traditional worklist systems rely on rigid rules that ignore critical context, radiologist specialization, current workload, fatigue levels, and case complexity. This creates a persistent challenge: radiologists cherry-pick easier, higher-value cases while avoiding complex studies, leading to diagnostic delays and increased costs. Research across 62 hospitals analyzing 2.2 million studies found […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/20471.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Intelligent, radiology, workflow, optimization, with, agents</media:keywords>
</item>

<item>
<title>Integrating AWS API MCP Server with Amazon Quick using Amazon Bedrock AgentCore Runtime</title>
<link>https://news.jatlink.uk/11734</link>
<guid>https://news.jatlink.uk/11734</guid>
<description><![CDATA[ This post shows you how to use Amazon Bedrock AgentCore Runtime with Model Context Protocol (MCP) support to connect Amazon Quick with AWS services through the AWS API MCP Server, creating a conversational AI assistant that translates natural language into AWS Command Line Interface (AWS CLI) commands, without the need to switch between tools during critical moments. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/20268-1.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Integrating, AWS, API, MCP, Server, with, Amazon, Quick, using, Amazon, Bedrock, AgentCore, Runtime</media:keywords>
</item>

<item>
<title>Break the context window barrier with Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/11736</link>
<guid>https://news.jatlink.uk/11736</guid>
<description><![CDATA[ In this post, you will learn how to implement Recursive Language Models (RLM) using Amazon Bedrock AgentCore Code Interpreter and the Strands Agents SDK. By the end, you will know how to process documents of varying lengths, with no upper bound on context size, use Bedrock AgentCore Code Interpreter as persistent working memory for iterative document analysis, and orchestrate sub-large language model (sub-LLM) calls from within a sandboxed Python environment to analyze specific document sections. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/21/20487.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Break, the, context, window, barrier, with, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Build AI&amp;powered dashboard automation agents with NLP on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/11712</link>
<guid>https://news.jatlink.uk/11712</guid>
<description><![CDATA[ This solution combines the power of Amazon Bedrock AgentCore, Strands Agents, and Amazon Quick transforms to deliver a secure, scalable, and intelligent system for building and operating AI agents while transforming data into actionable business insights. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/20/image-35.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 17:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, AI-powered, dashboard, automation, agents, with, NLP, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Announcing OpenAI&amp;compatible API support for Amazon SageMaker AI endpoints</title>
<link>https://news.jatlink.uk/11680</link>
<guid>https://news.jatlink.uk/11680</guid>
<description><![CDATA[ Today, Amazon SageMaker AI introduces OpenAI-compatible API support for real-time inference endpoints. If you use the OpenAI SDK, LangChain, or Strands Agents, you can now invoke models on SageMaker AI by changing only your endpoint URL. You don’t need a custom client, a SigV4 wrapper, or code rewrites. Overview With this launch, SageMaker AI endpoints […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/20/21074.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 21 May 2026 05:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Announcing, OpenAI-compatible, API, support, for, Amazon, SageMaker, endpoints</media:keywords>
</item>

<item>
<title>Build real&amp;time voice applications with Amazon SageMaker AI and vLLM</title>
<link>https://news.jatlink.uk/11651</link>
<guid>https://news.jatlink.uk/11651</guid>
<description><![CDATA[ Voice agents, live captioning, contact center analytics, and accessibility tools all depend on real-time speech-to-text, where your application streams audio in and receives transcription back simultaneously over a single persistent connection. Traditional request-response inference falls short here because transcription cannot begin until the entire audio recording has been received, adding latency that breaks the real-time […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/20/20779.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 20 May 2026 21:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, real-time, voice, applications, with, Amazon, SageMaker, and, vLLM</media:keywords>
</item>

<item>
<title>Multimodal evaluators: MLLM&amp;as&amp;a&amp;judge for image&amp;to&amp;text tasks in Strands Evals</title>
<link>https://news.jatlink.uk/11650</link>
<guid>https://news.jatlink.uk/11650</guid>
<description><![CDATA[ If you’re building visual shopping, image or document understanding, or chart analysis, you need a way to verify whether your model’s response is actually grounded in the source image. A text-only evaluator cannot tell you whether a caption faithfully describes an image, whether an extracted invoice total matches the document, or whether a screen summary […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/20/21039.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 20 May 2026 21:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Multimodal, evaluators:, MLLM-as-a-judge, for, image-to-text, tasks, Strands, Evals</media:keywords>
</item>

<item>
<title>Implementing programmatic tool calling on Amazon Bedrock</title>
<link>https://news.jatlink.uk/11564</link>
<guid>https://news.jatlink.uk/11564</guid>
<description><![CDATA[ In this post, we show three ways to implement Programmatic tool calling (PTC) on Amazon Bedrock: a self-hosted Docker sandbox on ECS for maximum control, a managed solution using Amazon Bedrock AgentCore Code Interpreter, and an Anthropic SDK-compatible path through a proxy for teams that prefer that developer experience. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/19/ml-20707.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 19 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Implementing, programmatic, tool, calling, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Scalable voice agent design with Amazon Nova Sonic: multi&amp;agent, tools, and session segmentation</title>
<link>https://news.jatlink.uk/11561</link>
<guid>https://news.jatlink.uk/11561</guid>
<description><![CDATA[ In this post, you’ll learn how to use Amazon Nova Sonic, Amazon Bedrock AgentCore, and Strands BidiAgent to build scalable, maintainable voice agents that handle these challenges efficiently, resulting in more responsive and intelligent customer interactions. We’ll explore three popular architectural patterns for voice agents, highlighting their trade-offs and best practices for minimizing latency. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/19/ml-20826.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 19 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Scalable, voice, agent, design, with, Amazon, Nova, Sonic:, multi-agent, tools, and, session, segmentation</media:keywords>
</item>

<item>
<title>Extending conversational memory in Kiro CLI using Amazon Bedrock AgentCore Memory</title>
<link>https://news.jatlink.uk/11562</link>
<guid>https://news.jatlink.uk/11562</guid>
<description><![CDATA[ In this post, we demonstrate how you can extend the conversational memory of Kiro CLI by implementing a custom Model Context Protocol (MCP) server that integrates with Amazon Bedrock AgentCore Memory. You can use Kiro CLI to interact with AI agents of Kiro directly from your terminal. Amazon Bedrock AgentCore Memory is a fully managed service that allows AI agents to retain information from past interactions, creating more intelligent and context-aware conversations. By implementing a custom MCP server, you can provide Kiro CLI with tools to store and retrieve conversation context, monitor memory usage, and manage the underlying Bedrock Agent Core Memory infrastructure. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-19844/ml_19844_blog_video_final.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 19 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Extending, conversational, memory, Kiro, CLI, using, Amazon, Bedrock, AgentCore, Memory</media:keywords>
</item>

<item>
<title>Accelerate ML feature pipelines with new capabilities in Amazon SageMaker Feature Store</title>
<link>https://news.jatlink.uk/11563</link>
<guid>https://news.jatlink.uk/11563</guid>
<description><![CDATA[ Today, we’re announcing three new capabilities available in SageMaker Python SDK v3.8.0. In this post, we walk through each capability with code examples you can use to get started. For complete end-to-end walkthroughs, see the accompanying notebooks for Lake Formation governance and Iceberg table properties in the SageMaker Python SDK repository. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/19/ml-21005.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 19 May 2026 21:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Accelerate, feature, pipelines, with, new, capabilities, Amazon, SageMaker, Feature, Store</media:keywords>
</item>

<item>
<title>Prompting Amazon Nova 2 for content moderation</title>
<link>https://news.jatlink.uk/11497</link>
<guid>https://news.jatlink.uk/11497</guid>
<description><![CDATA[ In this post, you learn how to prompt Amazon Nova 2 Lite for content moderation using structured and free-form approaches, grounded in the MLCommons AILuminate Assessment Standard. The prompting techniques use the AILuminate taxonomy as an example, but they work equally well with your own custom moderation policy. You can swap in your own category definitions and the prompt structure stays the same. We also benchmark the content moderation capabilities of Amazon Nova 2 Lite against several foundation models (FMs) on three public datasets. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/18/ml-20856.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 18 May 2026 23:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Prompting, Amazon, Nova, for, content, moderation</media:keywords>
</item>

<item>
<title>Aderant transforms cloud operations with Amazon Quick</title>
<link>https://news.jatlink.uk/11483</link>
<guid>https://news.jatlink.uk/11483</guid>
<description><![CDATA[ In this post, we share how Aderant used the AI-powered capabilities of Amazon Quick to unify search across six vendor systems and automate documentation workflows, achieving 90 percent faster search times and 75 percent documentation acceleration, and how others can apply these approaches to their operations. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/18/ML-20523.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 18 May 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Aderant, transforms, cloud, operations, with, Amazon, Quick</media:keywords>
</item>

<item>
<title>Integrate Atlassian Confluence Cloud with Amazon Quick</title>
<link>https://news.jatlink.uk/11484</link>
<guid>https://news.jatlink.uk/11484</guid>
<description><![CDATA[ In this post, you will learn how to set up the Confluence Cloud integration with Quick. This includes creating a knowledge base for semantic search, setting up Actions to query and manage Confluence pages, and organizing resources in Quick Spaces. Quick integrates with your current enterprise technology stack, from internal knowledge repositories and corporate intranets to business-critical applications and AWS data services. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/18/ml-19951.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 18 May 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Integrate, Atlassian, Confluence, Cloud, with, Amazon, Quick</media:keywords>
</item>

<item>
<title>Build custom code&amp;based evaluators in Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/11485</link>
<guid>https://news.jatlink.uk/11485</guid>
<description><![CDATA[ In this post, you will implement four Lambda-based custom code evaluators for a financial market-intelligence agent, register each with AgentCore, and run them in on-demand and online modes. You will also see how to combine custom code-based evaluators with built-in evaluators and how to call other AWS services for grounded fact-checking, PII detection, and real-time alerting. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/18/ml-20799.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 18 May 2026 19:00:14 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, custom, code-based, evaluators, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Restrict access to sensitive documents in your Amazon Quick knowledge bases for Amazon S3</title>
<link>https://news.jatlink.uk/11296</link>
<guid>https://news.jatlink.uk/11296</guid>
<description><![CDATA[ In this post, we walk through how to configure document-level ACLs for your S3 knowledge base in Amazon Quick. You will learn how to set up and verify an ACL configuration that enforces document-level permissions across chat and automated workflows. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/15/ml-20551.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 15 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Restrict, access, sensitive, documents, your, Amazon, Quick, knowledge, bases, for, Amazon</media:keywords>
</item>

<item>
<title>From siloed data to unified insights: Cross&amp;account Athena Access for Amazon Quick</title>
<link>https://news.jatlink.uk/11214</link>
<guid>https://news.jatlink.uk/11214</guid>
<description><![CDATA[ Today, we&#039;re announcing cross-account Athena access for Amazon Quick. With this feature, customers can query Athena data in other AWS accounts using AWS Identity and Access Management (IAM) role chaining, with query costs billed to the account where the data resides. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/13/ML-20930-image-1.jpg" length="49398" type="image/jpeg"/>
<pubDate>Thu, 14 May 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, siloed, data, unified, insights:, Cross-account, Athena, Access, for, Amazon, Quick</media:keywords>
</item>

<item>
<title>Control where your AI agents can browse with Chrome enterprise policies on Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/11215</link>
<guid>https://news.jatlink.uk/11215</guid>
<description><![CDATA[ In this post, you will configure Chrome enterprise policies to restrict a browser agent to a specific website, observe the policy enforcement through session recording, and demonstrate custom root CA certificates using a public test site. The walkthrough produces a working solution that researches Amazon Bedrock AgentCore documentation while operating under enterprise browser restrictions. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/14/ml-20775.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 14 May 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Control, where, your, agents, can, browse, with, Chrome, enterprise, policies, Amazon, Bedrock, AgentCore</media:keywords>
</item>

<item>
<title>Improve bot accuracy with Amazon Lex Assisted NLU</title>
<link>https://news.jatlink.uk/11212</link>
<guid>https://news.jatlink.uk/11212</guid>
<description><![CDATA[ In this post, you will learn how to implement Assisted NLU effectively. You will learn how to improve your bot design with effective intent and slot descriptions, validate your implementation using Test Workbench, and plan your transition from traditional NLU to Assisted NLU for both new and existing bots. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/14/ml-20312.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 14 May 2026 19:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Improve, bot, accuracy, with, Amazon, Lex, Assisted, NLU</media:keywords>
</item>

<item>
<title>Real&amp;time voice agents with Stream Vision Agents and Amazon Nova 2 Sonic</title>
<link>https://news.jatlink.uk/11213</link>
<guid>https://news.jatlink.uk/11213</guid>
<description><![CDATA[ In this post, you learn how to combine Stream&#039;s Vision Agents open-source framework with Amazon Bedrock and Amazon Nova 2 Sonic to build real-time voice agents that can be production-ready in minutes. You&#039;ll learn how the integration works under the hood, walk through code examples, and explore advanced capabilities like function calling, automatic reconnection, and multilingual voice support. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/14/ml-20223.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 14 May 2026 19:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Real-time, voice, agents, with, Stream, Vision, Agents, and, Amazon, Nova, Sonic</media:keywords>
</item>

<item>
<title>Build financial document processing with Pulse AI and Amazon Bedrock</title>
<link>https://news.jatlink.uk/11138</link>
<guid>https://news.jatlink.uk/11138</guid>
<description><![CDATA[ This post demonstrates how to build a documentation extraction and model fine-tuning pipeline that addresses challenges when processing the complex financial documents. By combining Pulse AI&#039;s advanced document understanding capabilities with the powerful AI services of Amazon Bedrock, organizations can achieve enterprise-grade accuracy and extract contextually relevant financial insights at scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/13/ml-19858.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 13 May 2026 23:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, financial, document, processing, with, Pulse, and, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Fine&amp;tune LLM with Databricks Unity Catalog and Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/11120</link>
<guid>https://news.jatlink.uk/11120</guid>
<description><![CDATA[ In this post, we demonstrate how to build a secure, complete LLM fine-tuning workflow that integrates Unity Catalog with Amazon SageMaker AI using Amazon EMR Serverless for preprocessing. The solution shows how to securely access governed data, maintain lineage across services, fine-tune the Ministral-3-3B-Instruct model, and register trained artifacts back into Unity Catalog. With this approach, you can continue using your existing services while preserving central governance, tracking data lineage without compromising security or compliance requirements. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/13/ml-19973.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 13 May 2026 19:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Fine-tune, LLM, with, Databricks, Unity, Catalog, and, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Build real&amp;time voice streaming applications with Amazon Nova Sonic and WebRTC</title>
<link>https://news.jatlink.uk/11118</link>
<guid>https://news.jatlink.uk/11118</guid>
<description><![CDATA[ Building end-to-end live streaming applications with real-time voice interaction presents several challenges. This post introduces a solution based on Amazon Nova 2 Sonic (Nova Sonic) and Amazon Kinesis Video Streams WebRTC (WebRTC) that addresses these challenges. In this post, we’ll walk through the solution architecture, implementation patterns, and two real-world scenario examples. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/13/ml-20027.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 13 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, real-time, voice, streaming, applications, with, Amazon, Nova, Sonic, and, WebRTC</media:keywords>
</item>

<item>
<title>Securing AI agents: How AWS and Cisco AI Defense scale MCP and A2A deployments</title>
<link>https://news.jatlink.uk/11119</link>
<guid>https://news.jatlink.uk/11119</guid>
<description><![CDATA[ The Cisco and AWS partnership addresses three challenges enterprises face when scaling AI agents: visibility gaps, security bottlenecks, and compliance risks. In this post, we explore how you can overcome AI security challenges through automated scanning and unified governance. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/13/ml-20700.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 13 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Securing, agents:, How, AWS, and, Cisco, Defense, scale, MCP, and, A2A, deployments</media:keywords>
</item>

<item>
<title>How Amazon Finance streamlines regulatory inquiries by using generative AI on AWS</title>
<link>https://news.jatlink.uk/11040</link>
<guid>https://news.jatlink.uk/11040</guid>
<description><![CDATA[ In this post, we demonstrate how Amazon FinTech teams are using Amazon Bedrock and other AWS services to build a scalable AI application to transform how regulatory inquiries are handled. Each team using this solution creates and maintains its own dedicated knowledge base, populated with that team&#039;s specific documents and reference materials. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/30/image-1-14-1119x630.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 12 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Amazon, Finance, streamlines, regulatory, inquiries, using, generative, AWS</media:keywords>
</item>

<item>
<title>Automate schema generation for intelligent document processing</title>
<link>https://news.jatlink.uk/11041</link>
<guid>https://news.jatlink.uk/11041</guid>
<description><![CDATA[ In this post, we&#039;ll show you how our multi-document discovery feature solves this problem. It serves as an automated pre-processing step, analyzing unknown documents, clustering them by type, and generating schemas ready for the IDP Accelerator. You&#039;ll learn how the new capability uses visual embeddings for automatic clustering and agents for schema generation. We&#039;ll also walk you through running the solution on your own document collections. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-20447/multidoc_discovery.mp4" length="49398" type="image/jpeg"/>
<pubDate>Tue, 12 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, schema, generation, for, intelligent, document, processing</media:keywords>
</item>

<item>
<title>Navigating EU AI Act requirements for LLM fine&amp;tuning on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/11042</link>
<guid>https://news.jatlink.uk/11042</guid>
<description><![CDATA[ In this post, we show you how to set up FLOPs tracking during LLM fine-tuning using the open source Fine-Tuning FLOPs Meter toolkit on Amazon SageMaker AI. You learn how to determine your compliance status with a single configuration flag and generate audit-ready documentation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/12/ml-20303.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 12 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Navigating, Act, requirements, for, LLM, fine-tuning, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Building web search&amp;enabled agents with Strands and Exa</title>
<link>https://news.jatlink.uk/10978</link>
<guid>https://news.jatlink.uk/10978</guid>
<description><![CDATA[ In this post, you will learn how to set up the Exa integration in Strands Agents, understand the two core tools it exposes, and walk through real-world use cases that show how agents use web search to complete multi-step tasks. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/11/ml-19612.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 11 May 2026 23:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, web, search-enabled, agents, with, Strands, and, Exa</media:keywords>
</item>

<item>
<title>Introducing Claude Platform on AWS: Anthropic’s native platform, through your AWS account</title>
<link>https://news.jatlink.uk/10979</link>
<guid>https://news.jatlink.uk/10979</guid>
<description><![CDATA[ Today, we&#039;re excited to announce the general availability of Claude Platform on AWS. Claude Platform on AWS is a new service that gives customers direct access to Anthropic&#039;s native Claude Platform experience through their AWS account, with no separate credentials, contracts, or billing relationships required. AWS is the first cloud provider to offer access to the native Claude Platform experience. In this post, we explore how Claude Platform on AWS works and how you can start using it today. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ml-20969/figure2.mp4" length="49398" type="image/jpeg"/>
<pubDate>Mon, 11 May 2026 23:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Claude, Platform, AWS:, Anthropic’s, native, platform, through, your, AWS, account</media:keywords>
</item>

<item>
<title>Manufacturing intelligence with Amazon Nova Multimodal Embeddings</title>
<link>https://news.jatlink.uk/10961</link>
<guid>https://news.jatlink.uk/10961</guid>
<description><![CDATA[ In this post, we build a multimodal retrieval system for aerospace manufacturing documents using Amazon Nova Multimodal Embeddings on Amazon Bedrock and Amazon S3 Vectors. We evaluate the system on 26 manufacturing queries and compare generation quality between a text-only pipeline and the multimodal pipeline. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/11/ml-20830.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 11 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Manufacturing, intelligence, with, Amazon, Nova, Multimodal, Embeddings</media:keywords>
</item>

<item>
<title>How Miro uses Amazon Bedrock to boost software bug routing accuracy and improve time&amp;to&amp;resolution from days to hours</title>
<link>https://news.jatlink.uk/10962</link>
<guid>https://news.jatlink.uk/10962</guid>
<description><![CDATA[ In this post, we dive deep into the architecture and techniques we used to improve Miro’s bug routing, achieving six times fewer team reassignments and five times shorter time-to-resolution powered by Amazon Bedrock. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/11/ml-18722.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 11 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Miro, uses, Amazon, Bedrock, boost, software, bug, routing, accuracy, and, improve, time-to-resolution, from, days, hours</media:keywords>
</item>

<item>
<title>Amazon Quick: Accelerating the path from enterprise data to AI&amp;powered decisions</title>
<link>https://news.jatlink.uk/10963</link>
<guid>https://news.jatlink.uk/10963</guid>
<description><![CDATA[ Amazon Quick helps turn your large enterprise data into fast and accurate AI-powered decisions. In this post, you will learn about five new capabilities of Amazon Quick that accelerate how data professionals deliver trusted AI-powered insights at enterprise scale. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/11/ml-21014.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 11 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Quick:, Accelerating, the, path, from, enterprise, data, AI-powered, decisions</media:keywords>
</item>

<item>
<title>Halliburton enhances seismic workflow creation with Amazon Bedrock and Generative AI</title>
<link>https://news.jatlink.uk/10747</link>
<guid>https://news.jatlink.uk/10747</guid>
<description><![CDATA[ In this post, we&#039;ll explore how we built a proof-of-concept that converts natural language queries into executable seismic workflows while providing a question-answering capability for Halliburton&#039;s Seismic Engine tools and documentation. We&#039;ll cover the technical details of the solution, share evaluation results showing workflow acceleration of up to 95%, and discuss key learnings that can help other organizations enhance their complex technical workflows with generative AI. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/08/ml-20026.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 08 May 2026 15:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Halliburton, enhances, seismic, workflow, creation, with, Amazon, Bedrock, and, Generative</media:keywords>
</item>

<item>
<title>Secure short&amp;term GPU capacity for ML workloads with EC2 Capacity Blocks for ML and SageMaker training plans</title>
<link>https://news.jatlink.uk/10679</link>
<guid>https://news.jatlink.uk/10679</guid>
<description><![CDATA[ In this post, you will learn how to secure reserved GPU capacity for short-term workloads using Amazon Elastic Compute Cloud (Amazon EC2) Capacity Blocks for ML and Amazon SageMaker training plans. These solutions can address GPU availability challenges when you need short-term capacity for load testing, model validation, time-bound workshops, or preparing inference capacity ahead of a release. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/07/ml-20156.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 07 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Secure, short-term, GPU, capacity, for, workloads, with, EC2, Capacity, Blocks, for, and, SageMaker, training, plans</media:keywords>
</item>

<item>
<title>Overcoming reward signal challenges: Verifiable rewards&amp;based reinforcement learning with GRPO on SageMaker AI</title>
<link>https://news.jatlink.uk/10680</link>
<guid>https://news.jatlink.uk/10680</guid>
<description><![CDATA[ In this post, you will learn how to implement reinforcement learning with verifiable rewards (RLVR) to introduce verification and transparency into reward signals to improve training performance. This approach works best when outputs can be objectively verified for correctness, such as in mathematical reasoning, code generation, or symbolic manipulation tasks. You will also learn how to layer techniques like Group Relative Policy Optimization (GRPO) and few-shot examples to further improve results. You’ll use the GSM8K dataset (Grade School Math 8K: a collection of grade school math problems) to improve math problem solving accuracy, but the techniques used here can be adapted to a wide variety of other use cases. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/07/ml-20356.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 07 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Overcoming, reward, signal, challenges:, Verifiable, rewards-based, reinforcement, learning, with, GRPO, SageMaker</media:keywords>
</item>

<item>
<title>Agents that transact: Introducing Amazon Bedrock AgentCore Payments, built with Coinbase and Stripe</title>
<link>https://news.jatlink.uk/10657</link>
<guid>https://news.jatlink.uk/10657</guid>
<description><![CDATA[ Today, we&#039;re announcing a preview of Amazon Bedrock AgentCore Payments, a new set of features in Amazon Bedrock AgentCore that enables AI agents to instantly access and pay for what they use. AgentCore Payments was developed in partnership with Coinbase and Stripe. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/06/images-ml-20991-featured.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 07 May 2026 15:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agents, that, transact:, Introducing, Amazon, Bedrock, AgentCore, Payments, built, with, Coinbase, and, Stripe</media:keywords>
</item>

<item>
<title>Cost effective deployment of vision&amp;language models for pet behavior detection on AWS Inferentia2</title>
<link>https://news.jatlink.uk/10592</link>
<guid>https://news.jatlink.uk/10592</guid>
<description><![CDATA[ Tomofun, the Taiwan-headquartered pet-tech startup behind the Furbo Pet Camera, is redefining how pet owners interact with their pets remotely. To reduce costs and maintain accuracy, Tomofun turned to EC2 Inf2 instances powered by AWS Inferentia2, the Amazon purpose-built AI chips. In this post, we walk through the following sections in detail. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/06/ml-19636.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 06 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Cost, effective, deployment, vision-language, models, for, pet, behavior, detection, AWS, Inferentia2</media:keywords>
</item>

<item>
<title>Introducing agent quality optimization in AgentCore, now in preview</title>
<link>https://news.jatlink.uk/10520</link>
<guid>https://news.jatlink.uk/10520</guid>
<description><![CDATA[ Generate recommendations from production traces, validate them with batch evaluation and A/B testing, and ship with confidence. AI agents that perform well at launch don’t stay that way. As models evolve, user behavior shifts, and prompts get reused in new contexts they were never designed for. Agent quality quietly degrades. In most teams, the improvement […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/05/ml-20827-1.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 05 May 2026 23:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, agent, quality, optimization, AgentCore, now, preview</media:keywords>
</item>

<item>
<title>How Hapag&amp;Lloyd uses Amazon Bedrock to transform customer feedback into actionable insights</title>
<link>https://news.jatlink.uk/10502</link>
<guid>https://news.jatlink.uk/10502</guid>
<description><![CDATA[ Hapag-Lloyd&#039;s Digital Customer Experience and Engineering team, distributed between Hamburg and Gdańsk, drives digital innovation by developing and maintaining customer-facing web and mobile products. In this post, we walk you through our generative AI–powered feedback analysis solution built using Amazon Bedrock, Elasticsearch, and open-source frameworks like LangChain and LangGraph ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/05/ml-19061.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 05 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Hapag-Lloyd, uses, Amazon, Bedrock, transform, customer, feedback, into, actionable, insights</media:keywords>
</item>

<item>
<title>Streamlining generative AI development with MLflow v3.10 on Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/10503</link>
<guid>https://news.jatlink.uk/10503</guid>
<description><![CDATA[ Today, we’re excited to announce that Amazon SageMaker AI MLflow Apps now support MLflow version 3.10, bringing enhanced capabilities for generative AI development and streamlined experiment tracking to your generative AI workflows. Building on the foundations established with Amazon SageMaker AI MLflow Apps, this latest version introduces powerful new features for observability, evaluation, and generative […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/05/20877-launch.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 05 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Streamlining, generative, development, with, MLflow, v3.10, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Introducing OS Level Actions in Amazon Bedrock AgentCore Browser</title>
<link>https://news.jatlink.uk/10504</link>
<guid>https://news.jatlink.uk/10504</guid>
<description><![CDATA[ We’re announcing OS Level Actions for AgentCore Browser. This new capability unblocks these scenarios by exposing direct OS control through the InvokeBrowser API, so agents can interact with content visible on the screen, not only what&#039;s accessible through the browser&#039;s web layer. By combining full-desktop screenshots with mouse and keyboard control at the OS level, agents can observe native UI, reason about it, and act on it within the same session. This post walks through how OS Level Actions work, what actions are supported, and how to get started. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/05/ml-20810.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 05 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Level, Actions, Amazon, Bedrock, AgentCore, Browser</media:keywords>
</item>

<item>
<title>Secure AI agents with Amazon Bedrock AgentCore Identity on Amazon ECS</title>
<link>https://news.jatlink.uk/10505</link>
<guid>https://news.jatlink.uk/10505</guid>
<description><![CDATA[ AI agents in production require secure access to external services. Amazon Bedrock AgentCore Identity, available as a standalone service, secures how your AI agents access external services whether they run on compute platforms like Amazon ECS, Amazon EKS, AWS Lambda, or on-premises. This post implements Authorization Code Grant (3-legged OAuth) on Amazon ECS with secure session binding and scoped tokens. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/05/ml-20517.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 05 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Secure, agents, with, Amazon, Bedrock, AgentCore, Identity, Amazon, ECS</media:keywords>
</item>

<item>
<title>Intelligence&amp;driven message defense and insights using Amazon Bedrock</title>
<link>https://news.jatlink.uk/10506</link>
<guid>https://news.jatlink.uk/10506</guid>
<description><![CDATA[ In this post, you will learn how you can use Amazon Nova Foundation Models in Amazon Bedrock to apply generative AI techniques for both business protection and enhancement. You can identify obvious and disguised attempts at direct contact while gaining valuable insights into customer sentiment and service improvement opportunities. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/05/ml-18644.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 05 May 2026 19:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Intelligence-driven, message, defense, and, insights, using, Amazon, Bedrock</media:keywords>
</item>

<item>
<title>Introducing the agent quality loop: AgentCore Optimization now in preview</title>
<link>https://news.jatlink.uk/10451</link>
<guid>https://news.jatlink.uk/10451</guid>
<description><![CDATA[ Generate recommendations from production traces, validate them with batch evaluation and A/B testing, and ship with confidence. AI agents that perform well at launch don’t stay that way. As models evolve, user behavior shifts, and prompts get reused in new contexts they were never designed for. Agent quality quietly degrades. In most teams, the improvement […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/04/ml-20827.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 05 May 2026 03:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, the, agent, quality, loop:, AgentCore, Optimization, now, preview</media:keywords>
</item>

<item>
<title>Capacity&amp;aware inference: Automatic instance fallback for SageMaker AI endpoints</title>
<link>https://news.jatlink.uk/10420</link>
<guid>https://news.jatlink.uk/10420</guid>
<description><![CDATA[ Today, Amazon SageMaker AI introduces capacity aware instance pool for new and existing inference endpoints. You define a prioritized list of instance types, and SageMaker AI automatically works through your list whenever capacity is constrained at creation, during scale-out, and during scale-in. Your endpoint provisions on available AI Infrastructure without manual intervention. This capability is available for Single Model Endpoints, Inference Component-based endpoints, and Asynchronous Inference endpoints. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/04/20949.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 04 May 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Capacity-aware, inference:, Automatic, instance, fallback, for, SageMaker, endpoints</media:keywords>
</item>

<item>
<title>Agent&amp;guided workflows to accelerate model customization in Amazon SageMaker AI</title>
<link>https://news.jatlink.uk/10416</link>
<guid>https://news.jatlink.uk/10416</guid>
<description><![CDATA[ Amazon SageMaker AI now offers an agentic experience that changes this. Developers describe their use case using natural language, and the AI coding agent streamlines the entire journey, from use case definition and data preparation through technique selection, evaluation, and deployment. In this post, we walk you through the model customization lifecycle using SageMaker AI agent skills. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/04/ml-20721.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 04 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Agent-guided, workflows, accelerate, model, customization, Amazon, SageMaker</media:keywords>
</item>

<item>
<title>Generate dashboards from natural language prompts in Amazon Quick</title>
<link>https://news.jatlink.uk/10417</link>
<guid>https://news.jatlink.uk/10417</guid>
<description><![CDATA[ Building meaningful dashboards demands hours of manual setup, even for experienced BI professionals. Amazon Quick now generates complete multi-sheet dashboards from natural language prompts, taking you from one or more datasets to a production-ready analysis in minutes. Data analysts building recurring operations reports, program managers preparing a leadership review, or engineers exploring a new dataset can […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/04/20708_0504-2.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 04 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Generate, dashboards, from, natural, language, prompts, Amazon, Quick</media:keywords>
</item>

<item>
<title>From data lake to AI&amp;ready analytics: Introducing new data source with S3 Tables in Amazon Quick</title>
<link>https://news.jatlink.uk/10418</link>
<guid>https://news.jatlink.uk/10418</guid>
<description><![CDATA[ Amazon Quick introduces Amazon S3 Tables (Apache Iceberg tables) as a new data source. With this feature, customers can directly query and visualize Apache Iceberg tables stored in an Amazon S3 table bucket without the need for intermediate data layers. In this post, we explored how Amazon Quick’s new Amazon S3 Tables data source enables near real-time analytics while streamlining modern data architectures. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/22/ML-20936-1-1260x543.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 04 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>From, data, lake, AI-ready, analytics:, Introducing, new, data, source, with, Tables, Amazon, Quick</media:keywords>
</item>

<item>
<title>Introducing Dataset Q&amp;amp;A: Expanding natural language querying for structured datasets in Amazon Quick</title>
<link>https://news.jatlink.uk/10419</link>
<guid>https://news.jatlink.uk/10419</guid>
<description><![CDATA[ In this post, you learn how to get started with Dataset Q&amp;A, explore real-world use cases with hands-on examples, and discover advanced capabilities like auto-discovery across all your data assets and multi-dataset querying in a single conversation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/29/ML-20685-image-6-867x630.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 04 May 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, Dataset, Q&amp;A:, Expanding, natural, language, querying, for, structured, datasets, Amazon, Quick</media:keywords>
</item>

<item>
<title>Beyond BI: How the Dataset Q&amp;amp;A feature of Amazon Quick powers the next generation of data decisions</title>
<link>https://news.jatlink.uk/10414</link>
<guid>https://news.jatlink.uk/10414</guid>
<description><![CDATA[ Business leaders across industries rely on operational dashboards as the shared source of truth that their teams execute against daily. But dashboards are built to answer known questions. When teams need to explore further, ad-hoc, multi-dimensional, or unforeseen questions, they hit a bottleneck. They wait hours or days for BI teams to build new views […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/04/20808-1.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 04 May 2026 19:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Beyond, BI:, How, the, Dataset, Q&amp;A, feature, Amazon, Quick, powers, the, next, generation, data, decisions</media:keywords>
</item>

<item>
<title>Introducing the agent performance loop: AgentCore Optimization now in preview</title>
<link>https://news.jatlink.uk/10415</link>
<guid>https://news.jatlink.uk/10415</guid>
<description><![CDATA[ Generate recommendations from production traces, validate them with batch evaluation and A/B testing, and ship with confidence. AI agents that perform well at launch don’t stay that way. As models evolve, user behavior shifts, and prompts get reused in new contexts they were never designed for. Agent quality quietly degrades. In most teams, the improvement […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/04/20827.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 04 May 2026 19:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Introducing, the, agent, performance, loop:, AgentCore, Optimization, now, preview</media:keywords>
</item>

<item>
<title>AWS Transform now automates BI migration to Amazon Quick in days</title>
<link>https://news.jatlink.uk/10229</link>
<guid>https://news.jatlink.uk/10229</guid>
<description><![CDATA[ In this post, we walk through the full journey, from setting up your migration workspace in AWS Transform to subscribing to partner agents through AWS Marketplace to unlocking Amazon Quick capabilities that change how your organization consumes data. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/01/ml-20713.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 01 May 2026 23:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AWS, Transform, now, automates, migration, Amazon, Quick, days</media:keywords>
</item>

<item>
<title>Reinforcement fine&amp;tuning with LLM&amp;as&amp;a&amp;judge</title>
<link>https://news.jatlink.uk/10157</link>
<guid>https://news.jatlink.uk/10157</guid>
<description><![CDATA[ In this post, we take a deeper look at how RLAIF or RL with LLM-as-a-judge works with Amazon Nova models effectively. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/30/ml-20696.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Apr 2026 23:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Reinforcement, fine-tuning, with, LLM-as-a-judge</media:keywords>
</item>

<item>
<title>Sun Finance automates ID extraction and fraud detection with generative AI on AWS</title>
<link>https://news.jatlink.uk/10140</link>
<guid>https://news.jatlink.uk/10140</guid>
<description><![CDATA[ In this post, we show how Sun Finance used Amazon Bedrock, Amazon Textract, and Amazon Rekognition to build an AI-powered identity verification (IDV) pipeline. The solution improved extraction accuracy from 79.7% to 90.8%, cut per-document costs by 91%, and reduced processing time from up to 20 hours to under 5 seconds. You&#039;ll learn how combining specialized OCR with large language model (LLM) structuring outperformed using either tool alone. You&#039;ll also learn how to architect a serverless fraud detection system using vector similarity search. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/30/ml-20316.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Apr 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Sun, Finance, automates, extraction, and, fraud, detection, with, generative, AWS</media:keywords>
</item>

<item>
<title>Unleashing Agentic AI Analytics on Amazon SageMaker with Amazon Athena and Amazon Quick</title>
<link>https://news.jatlink.uk/10141</link>
<guid>https://news.jatlink.uk/10141</guid>
<description><![CDATA[ This post demonstrates how agentic AI assistant from Amazon Quick transform data analytics into a self-service capability by using Amazon Simple Storage Service (Amazon S3) as a storage, Amazon SageMaker and AWS Glue for lakehouse, Amazon Athena for serverless SQL querying across multiple storage formats (S3 Table, Iceberg, and Parquet). ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/28/ml-20574.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Apr 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Unleashing, Agentic, Analytics, Amazon, SageMaker, with, Amazon, Athena, and, Amazon, Quick</media:keywords>
</item>

<item>
<title>Configuring Amazon Bedrock AgentCore Gateway for secure access to private resources</title>
<link>https://news.jatlink.uk/10142</link>
<guid>https://news.jatlink.uk/10142</guid>
<description><![CDATA[ In this post, you will configure Amazon Bedrock AgentCore Gateway to access private endpoints using Resource Gateway, a managed construct that provisions Elastic Network Interfaces (ENIs) directly inside your Amazon VPC, one per subnet. You will explore two implementation modes (managed and self-managed) and walk through three practical scenarios: connecting to a private Amazon API Gateway endpoint, integrating with a MCP server on Amazon Elastic Kubernetes Service (Amazon EKS), and accessing a private REST API. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/30/ml-20737.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Apr 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Configuring, Amazon, Bedrock, AgentCore, Gateway, for, secure, access, private, resources</media:keywords>
</item>

<item>
<title>AWS Generative AI Model Agility Solution: A comprehensive guide to migrating LLMs for generative AI production</title>
<link>https://news.jatlink.uk/10139</link>
<guid>https://news.jatlink.uk/10139</guid>
<description><![CDATA[ In this post, we introduce a systematic framework for LLM migration or upgrade in generative AI production, encompassing essential tools, methodologies, and best practices. The framework facilitates transitions between different LLMs by providing robust protocols for prompt conversion and optimization. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/13/ML-17637-image-1.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 30 Apr 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>AWS, Generative, Model, Agility, Solution:, comprehensive, guide, migrating, LLMs, for, generative, production</media:keywords>
</item>

<item>
<title>Organizing Agents’ memory at scale: Namespace design patterns in AgentCore Memory</title>
<link>https://news.jatlink.uk/10067</link>
<guid>https://news.jatlink.uk/10067</guid>
<description><![CDATA[ In this post, you will learn how to design namespace hierarchies, choose the right retrieval patterns, and implement AWS Identity and Access Management (IAM)-based access control for AgentCore Memory. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/24/ML-20833-image-2-1260x393.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 29 Apr 2026 23:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Organizing, Agents’, memory, scale:, Namespace, design, patterns, AgentCore, Memory</media:keywords>
</item>

<item>
<title>Extracting contract insights with PwC’s AI&amp;driven annotation on AWS</title>
<link>https://news.jatlink.uk/10066</link>
<guid>https://news.jatlink.uk/10066</guid>
<description><![CDATA[ This post was co-written with Yash Munsadwala, Adam Hood, Justin Guse, and Hector Hernandez from PwC. Contract analysis often consumes significant time for legal, compliance, and procurement teams, especially when important insights are buried in lengthy, unstructured agreements. As contract volumes grow, finding specific clauses and assessing extracted terms can become increasingly difficult to scale. […] ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/27/AIDA_FeaturePhotoForBlog-1260x578.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 29 Apr 2026 23:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Extracting, contract, insights, with, PwC’s, AI-driven, annotation, AWS</media:keywords>
</item>

<item>
<title>Building AI&amp;ready data: Vanguard’s Virtual Analyst journey</title>
<link>https://news.jatlink.uk/10036</link>
<guid>https://news.jatlink.uk/10036</guid>
<description><![CDATA[ In this post, you&#039;ll learn how Vanguard built their Virtual Analyst solution by focusing on eight guiding principles of AI-ready data, the AWS services that powered their implementation, and the measurable business outcomes they achieved. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/29/ml-19986.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 29 Apr 2026 15:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, AI-ready, data:, Vanguard’s, Virtual, Analyst, journey</media:keywords>
</item>

<item>
<title>Run custom MCP proxies serverless on Amazon Bedrock AgentCore Runtime</title>
<link>https://news.jatlink.uk/10037</link>
<guid>https://news.jatlink.uk/10037</guid>
<description><![CDATA[ This post shows you how to deploy a serverless MCP proxy on Amazon Bedrock AgentCore Runtime that gives you a programmable layer to implement proper governance, controls, and observability aligned with an organization&#039;s security policies. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/29/ml-20371.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 29 Apr 2026 15:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Run, custom, MCP, proxies, serverless, Amazon, Bedrock, AgentCore, Runtime</media:keywords>
</item>

<item>
<title>Migrating a text agent to a voice assistant with Amazon Nova 2 Sonic</title>
<link>https://news.jatlink.uk/9967</link>
<guid>https://news.jatlink.uk/9967</guid>
<description><![CDATA[ In this post, we explore what it takes to migrate a traditional text agent into a conversational voice assistant using Amazon Nova 2 Sonic. We compare text and voice agent requirements, highlight design priorities for different use cases, break down agent architecture, and address common concerns like tools and sub-agents for reuse and system prompt adaptation. This post helps you navigate the migration process and avoid common pitfalls. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/28/ml-20642.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 28 Apr 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Migrating, text, agent, voice, assistant, with, Amazon, Nova, Sonic</media:keywords>
</item>

<item>
<title>NVIDIA Nemotron 3 Nano Omni model now available on Amazon SageMaker JumpStart</title>
<link>https://news.jatlink.uk/9968</link>
<guid>https://news.jatlink.uk/9968</guid>
<description><![CDATA[ Today, we are excited to announce the day zero availability of NVIDIA Nemotron 3 Nano Omni on Amazon SageMaker JumpStart. In this post, we walk through the model architecture and key capabilities of Nemotron 3 Nano Omni, explore the enterprise use cases it unlocks, and show you how to deploy and run inference using Amazon SageMaker JumpStart. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/28/ml-20974.png" length="49398" type="image/jpeg"/>
<pubDate>Tue, 28 Apr 2026 19:00:10 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>NVIDIA, Nemotron, Nano, Omni, model, now, available, Amazon, SageMaker, JumpStart</media:keywords>
</item>

<item>
<title>Build Strands Agents with SageMaker AI models and MLflow</title>
<link>https://news.jatlink.uk/9888</link>
<guid>https://news.jatlink.uk/9888</guid>
<description><![CDATA[ In this post, we demonstrate how to build AI agents using Strands Agents SDK with models deployed on SageMaker AI endpoints. You will learn how to deploy foundation models from SageMaker JumpStart, integrate them with Strands Agents, and establish production-grade observability using SageMaker Serverless MLflow for agent tracing. We also cover how to implement A/B testing across multiple model variants and evaluate agent performance using MLflow metrics and show how you can build, deploy, and continuously improve AI agents on infrastructure you control. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/27/ml-19842-feature-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 27 Apr 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, Strands, Agents, with, SageMaker, models, and, MLflow</media:keywords>
</item>

<item>
<title>How Popsa used Amazon Nova to inspire customers with personalised title suggestions</title>
<link>https://news.jatlink.uk/9889</link>
<guid>https://news.jatlink.uk/9889</guid>
<description><![CDATA[ In this post, we share how we applied Amazon Bedrock and the Amazon Nova family of models to reimagine our Title Suggestion feature. By combining metadata, computer vision, and retrieval-augmented generative AI, we now automatically generate creative, brand-aligned titles and subtitles across 12 languages. Using the unified API of Amazon Bedrock, Anthropic’s Claude 3 Haiku, and Amazon Nova Lite and Pro, we improved quality, reduced cost, and cut response times. This resulted in higher customer satisfaction, measurable uplifts in engagement and purchase rates, and over 5.5 million personalised titles generated in 2025. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/27/ml-19401-feaure-image.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 27 Apr 2026 19:00:13 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>How, Popsa, used, Amazon, Nova, inspire, customers, with, personalised, title, suggestions</media:keywords>
</item>

<item>
<title>Automate repetitive tasks with Amazon Quick Flows</title>
<link>https://news.jatlink.uk/9886</link>
<guid>https://news.jatlink.uk/9886</guid>
<description><![CDATA[ This post shows you how to build your first AI-powered workflow, using Amazon Quick, starting with a financial analysis tool and progressing to an advanced employee onboarding automation. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/27/ML-19871.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 27 Apr 2026 19:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Automate, repetitive, tasks, with, Amazon, Quick, Flows</media:keywords>
</item>

<item>
<title>Build and deploy an automatic sync solution for Amazon Bedrock Knowledge Bases</title>
<link>https://news.jatlink.uk/9887</link>
<guid>https://news.jatlink.uk/9887</guid>
<description><![CDATA[ In this post, we explore an automated solution that detects S3 events and triggers ingestion jobs while respecting service quotas and providing comprehensive monitoring. This serverless solution uses an event-driven architecture to keep your knowledge base current without overwhelming the Amazon Bedrock APIs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/27/ml-18250.png" length="49398" type="image/jpeg"/>
<pubDate>Mon, 27 Apr 2026 19:00:12 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Build, and, deploy, automatic, sync, solution, for, Amazon, Bedrock, Knowledge, Bases</media:keywords>
</item>

<item>
<title>Building Workforce AI Agents with Visier and Amazon Quick</title>
<link>https://news.jatlink.uk/9698</link>
<guid>https://news.jatlink.uk/9698</guid>
<description><![CDATA[ In this post, we show how connecting the Visier Workforce AI platform with Amazon Quick through Model Context Protocol (MCP) gives every knowledge worker a unified agentic workspace to ask questions in. Visier helps ground the workspace in live workforce data and the organizational context that surrounds it while letting your users act on the conversational results without switching tools. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/24/visier.png" length="49398" type="image/jpeg"/>
<pubDate>Fri, 24 Apr 2026 23:00:11 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Building, Workforce, Agents, with, Visier, and, Amazon, Quick</media:keywords>
</item>

<item>
<title>Amazon Quick for marketing: From scattered data to strategic action</title>
<link>https://news.jatlink.uk/9596</link>
<guid>https://news.jatlink.uk/9596</guid>
<description><![CDATA[ Amazon Quick changes how you work. You can set it up in minutes and by the end of the day, you will wonder how you ever worked without it. Quick connects with your applications, tools, and data, creating a personal knowledge graph that learns your priorities, preferences, and network. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/artifacts/DBSBlogs/ML-20786/Quick Demo_Marketing-Flow.mp4" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Apr 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, Quick, for, marketing:, From, scattered, data, strategic, action</media:keywords>
</item>

<item>
<title>Applying multimodal biological foundation models across therapeutics and patient care</title>
<link>https://news.jatlink.uk/9597</link>
<guid>https://news.jatlink.uk/9597</guid>
<description><![CDATA[ In this post, we&#039;ll explore how multimodal BioFMs work, showcase real-world applications in drug discovery and clinical development, and contextualize how AWS enables organizations to build and deploy multimodal BioFMs. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/21/ML-20310-image-1-new-1260x594.png" length="49398" type="image/jpeg"/>
<pubDate>Thu, 23 Apr 2026 19:00:09 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Applying, multimodal, biological, foundation, models, across, therapeutics, and, patient, care</media:keywords>
</item>

<item>
<title>Cost&amp;effective multilingual audio transcription at scale with Parakeet&amp;TDT and AWS Batch</title>
<link>https://news.jatlink.uk/9530</link>
<guid>https://news.jatlink.uk/9530</guid>
<description><![CDATA[ In this post, we walk through building a scalable, event-driven transcription pipeline that automatically processes audio files uploaded to Amazon Simple Storage Service (Amazon S3), and show you how to use Amazon EC2 Spot Instances and buffered streaming inference to further reduce costs. ]]></description>
<enclosure url="http://ia601608.us.archive.org/16/items/Expedition46/_01-15-15_EXP43-46_Preflight-Crew-News-Conference.wav" length="49398" type="image/jpeg"/>
<pubDate>Wed, 22 Apr 2026 23:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Cost-effective, multilingual, audio, transcription, scale, with, Parakeet-TDT, and, AWS, Batch</media:keywords>
</item>

<item>
<title>Amazon SageMaker AI now supports optimized generative AI inference recommendations</title>
<link>https://news.jatlink.uk/9531</link>
<guid>https://news.jatlink.uk/9531</guid>
<description><![CDATA[ Today, Amazon SageMaker AI  supports optimized generative AI inference recommendations. By delivering validated, optimal deployment configurations with performance metrics, Amazon SageMaker AI keeps your model developers focused on building accurate models, not managing infrastructure. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/22/ml-20661-1120x630.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 22 Apr 2026 23:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Amazon, SageMaker, now, supports, optimized, generative, inference, recommendations</media:keywords>
</item>

<item>
<title>Get to your first working agent in minutes: Announcing new features in Amazon Bedrock AgentCore</title>
<link>https://news.jatlink.uk/9532</link>
<guid>https://news.jatlink.uk/9532</guid>
<description><![CDATA[ Today, we&#039;re introducing new capabilities that further streamline the agent building experience, removing the infrastructure barriers that slow teams down at every stage of agent development from the first prototype through production deployment. ]]></description>
<enclosure url="http://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/22/ml-20892-1120x630.png" length="49398" type="image/jpeg"/>
<pubDate>Wed, 22 Apr 2026 23:00:08 +0100</pubDate>
<dc:creator>Jat AI</dc:creator>
<media:keywords>Get, your, first, working, agent, minutes:, Announcing, new, features, Amazon, Bedrock, AgentCore</media:keywords>
</item>

</channel>
</rss>