Grammy Award-winning percussionist Evelyn Glennie's new take on the Radiohead classic.

Go beyond the prompt to manage autonomous agentic systems

A tour of battle-tested command-line tools that make Claude Code a more capable agent by leaning on the Unix philosophy of composable tools that work with text streams. It also covers writing your own...

Not long ago, the craft of working with large language models was all about the prompt. You'd...

Not long ago, the craft of working with large language models was all about the prompt. You'd...

Developer Advocate @ AWS. I write about the cloud & Swift<br/>(opinions are my own)

Six implementations of the same tiny GPT language model — from pure Python to PyTorch, JAX, and MLX. Inspired by Andrej Karpathy's microGPT. - danilop/micro-gpt-and-beyond

At the end of 2025 I was happy to take a long break to enjoy the incredible summers that the southern hemisphere provides. I’m back and writing my first post in 2026 which also happens to be my last...

At the beginning of January, I tend to set my top resolutions for the year, a way to focus on what I want to achieve. If AI and cloud computing are on your resolution list, consider creating an AWS…

I had a problem. My Kiro setup had accumulated 14 MCP servers over time: AWS tools, web automation,...

After Amazon Bedrock introduced OpenAI-compatible application programming interfaces (APIs) through...

After Amazon Bedrock introduced OpenAI-compatible application programming interfaces (APIs) through...

This week at AWS re:Invent 2025, Amazon S3 Vectors reached general availability, bringing...

This week at AWS re:Invent 2025, Amazon S3 Vectors reached general availability, bringing...

Discover more about what's new at AWS with Amazon Bedrock now supports Responses API from OpenAI

The Strands Agents SDK, which was released as open source in May 2025, recently added TypeScript...

A model-driven approach to building AI agents in just a few lines of code. - GitHub - strands-agents/sdk-typescript: A model-driven approach to building AI agents in just a few lines of code.

Access fully managed foundation models from leading providers like Google, Kimi AI, MiniMax AI, Mistral AI, NVIDIA, OpenAI, and Qwen, including the new Mistral Large 3 and Ministral 3 3B, 8B, and 14B…

New Lambda capability lets you build applications that coordinate multiple steps reliably over extended periods—from seconds to up to one year—without paying for idle compute time when waiting for…

Scale vector storage and querying to new heights with S3 Vectors' general availability—now supporting up to 1 billion vectors per index, 100ms query latencies, and expanded regional availability,…

Build more natural voice interactions with enhanced speech-to-speech AI—now featuring multilingual conversations, dynamic speech control, crossmodal inputs, and improved telephony integration while…

Deploy AI agents with confidence using new quality evaluations and policy controls—enabling precise boundaries on agent actions, continuous quality monitoring, and experience-based learning while…

New program gives organizations unprecedented access to Nova model training, enabling them to build custom frontier models that deeply embed domain expertise without the traditional barriers of cost,…

New AWS service helps developers build AI agents that automate browser-based tasks like form filling, search & extract, shopping & booking, and QA testing—with over 90% reliability for enterprise…

New fast, cost-effective model supports extended thinking with adjustable reasoning depth, letting you control the balance between speed, intelligence, and cost while building AI applications for…

Discover our most impactful innovations across analytics, AI, compute, containers, security, and more throughout the conference week.

Discover more about what's new at AWS with AWS Service Reference Information now supports SDK Operation to Action mapping