When deploying diffusion models in design tools, image editors, and visual production workflows, developers must account for inference latency. Generating an... When deploying diffusion models in design tools, image editors, and visual production workflows, developers must acc…

Writing code got faster. The work around it didn't. See how you can plan, write code, review changes, and investigate production issues with GitHub Copilot, and what work still needs your judgment. The post Beyond code generation: A developer’s guide to agentic engineering app…

Many data-sharing architectures begin with a familiar pattern: A provider exports...

If you ingest data from your customers over SFTP or APIs, you have probably asked...

For Claude to learn from experience, it has to decide what’s worth remembering before it knows what’s next. Here’s how “dreaming” helps it organize memory and correct mistakes.

For AGI to benefit all of humanity, it should help people with the everyday tasks that matter most to them. So we built LifeVal, a new benchmark shaped by feedback from thousands of ChatGPT users on where they most want help from a personal assistant—from finding childcare to …

AI for Science grantees Jakob Macke, Daniel Gedon, and Stefan Wahl on how AI is starting to change how scientific models are built and interpreted.

A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.

During reinforcement learning (RL) post-training, training trajectories are generated on the fly by running inference with the current policy model. For... During reinforcement learning (RL) post-training, training trajectories are generated on the fly by running inference wit…

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. This post shows how two option…

As we built Amazon Quick, its agents grew from answering questions to taking actions, and the same primitives kept getting rebuilt under different names. This post shares the taxonomy we converged on — triggers, agents, capabilities, and learned context — found by decomposing …

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.

We put Claude in two EVE games to study how AI agents handle markets and teamwork, where they break down, and what safeguards they might need.

In Part 1 you built one governed agent. Part 2 scales the pattern to an enterprise: Amazon Bedrock AgentCore Gateway becomes the single front door and redeems Okta's grant, Cedar policies bind each tool to the agent, a second agent runs on Amazon EKS, and AgentCore Observabili…

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. In this first post of two, you build a task agent on Amazon Bedrock AgentCore that governs access through O…

Greenlight Financial resolves more than 90% of up to 4,000 monthly security and risk cases without human intervention using Luna, a tiered multi-agent system on Amazon Bedrock AgentCore. This post covers the architecture, episodic memory for continuous learning, and the expans…