AWS introduced a design pattern called Adjudicated Query that lets business users sweep tens of thousands of apartment leases for compliance through Amazon Quick's generative AI chat interface while p…
Amazon Web Services published a walkthrough for connecting Claude Desktop on Amazon Bedrock to Web Search through Amazon Bedrock AgentCore Gateway, using JWT-based inbound authentication. The setup fe…
Amazon Web Services detailed Amazon SageMaker AI multi-turn reinforcement learning (MTRL), a fine-tuning capability that trains LLM search agents across full multi-turn trajectories rather than single…
Amazon Web Services announced the public preview of AWS Well-Architected Agent, an AI-powered service that analyzes AWS environments and delivers contextual optimization recommendations across cost, s…
Amazon Web Services launched Live Data in Apps for Amazon Quick, letting AI-built Quick apps query governed Quick Sight datasets live at view time instead of relying on static build-time snapshots. Th…
NVIDIA NeMo Agent Toolkit (NAT) now supports Amazon S3 Vectors as a custom persistent memory provider, implemented through NAT's MemoryEditor interface with add_items(), search(), and remove_items() m…
Amazon Payments applied a multi-objective contextual multi-armed bandit on Amazon SageMaker AI to personalize a product acquisition funnel, reporting a high single-digit percentage relative lift in fi…
AWS published a step-by-step implementation guide for giving three environment types — AWS production workloads, developer laptops, and external or on-premises CI/CD pipelines — inference access to Cl…
Uniopen, the digital communication and membership platform from Taiwan's Uni-President Enterprises Group, adapted Amazon Nova 2 Lite to its retail moderation policies using supervised fine-tuning in A…
Amazon Web Services announced metadata pre-filtering for Amazon S3 Vectors, which evaluates a metadata filter before the similarity search and returns up to 5x more matching vectors on highly selectiv…
Amazon Web Services announced that Amazon Aurora PostgreSQL can now directly query Apache Iceberg and Apache Parquet data in a data lake, eliminating extract, transform, and load (ETL) pipelines that …
Amazon published a technical how-to showing how to build a claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions about insurance claims with citations, using the A…
Amazon Web Services introduced Runtime Instances for Amazon Bedrock AgentCore, a managed EC2-based compute option that supports agent sessions of up to 14 days, GPU access, persistent Amazon EBS stora…
Amazon Bedrock now serves Anthropic's Claude Opus 5, Claude Sonnet 5, and Claude Haiku 4.5 to customers in India through a new India geographic cross-Region inference profile that routes requests only…
OpenAI's GPT-6.1 Sol is now generally available on Amazon Bedrock, delivering what OpenAI calls near-Astra intelligence for agentic coding, computer use, and professional workloads. According to OpenA…
Amazon Web Services published a component-by-component guide to prompt engineering in Amazon Quick, detailing how Quick Research, Quick Flows, Quick Sight, chat agents, and action integrations each in…
AWS published an architecture for a contract intelligence platform that uses AI agents on Amazon Bedrock AgentCore to extract key fields from vendor contracts into a database, then answers portfolio-l…
XAI's Grok 4.7 is now available in the Amazon Bedrock model catalog, offering a 500K token context window and configurable reasoning effort at four levels: low, medium, high, and xhigh. The model is s…
Anthropic's Claude Sonnet 5.5 is now available on Amazon Bedrock and Claude Platform on AWS, AWS announced, offering lower cost per task for most work at faster speed than Sonnet 5. The model is posit…
AWS published Part 1 of a tutorial series showing how to deploy the Qwen3-TTS text-to-speech model on Amazon SageMaker AI using the AWS vLLM-Omni Deep Learning Container, streaming text in and audio o…