Official announcement · AWS Machine Learning ·
As we built Amazon Quick, its agents grew from answering questions to taking actions, and the same primitives kept getting rebuilt under different names.
OfficialAWS Machine Learning
Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so you can run a different model in each or take a right-sized fraction of a newer accelerator.
OfficialAWS Machine Learning
Learn how to build a serverless Model Context Protocol (MCP) server on Amazon ECS with AWS Fargate that gives AI agents secure, metadata-driven access to an enterprise data lake. Exposing a new dataset requires only a JSON file, with no per-dataset integration code.
OfficialAWS Machine Learning
In Part 1 you built one governed agent.
OfficialAWS Machine Learning
An AI agent that acts for a user raises an identity question that per-app OAuth and service accounts leave open: which agent may act for which user, and how you stop it.