Search AWS Educational Content

Introducing the managed agent harness in Amazon Bedrock AgentCore. Define your agent, pick a model, add tools, and run it in three API calls. No orchestration code. → https://go.aws/4cv5U7Y Want to learn more about Agent Harnesses? Check out this vid: https://go.aws/3Qu7VIT

Simplify building multi-step applications and AI workflows with Lambda durable functions. After turning on a simple configuration setting, you can write, test, and debug durable functions using your preferred programming languages and IDEs. Durability strengthens application resilience. You can preserve progress despite interruptions through built-in error handling, automatic retries, and recovery after failures.

Agent Toolkit for AWS gives AI coding agents the tools, knowledge, and guardrails they need to work effectively with AWS services. Instead of relying on agents' general knowledge of AWS -- which can be outdated or incomplete -- it provides access to up-to-date documentation, best practices, and tested procedures that improve success rates and reduce wasted effort.

Twitch stream from aws

The future of AI agent development is here, and it's more accessible than ever. Built and battle-tested by Amazon and AWS teams, Strands Agents SDK enables developers to create production-ready AI agents in days instead of months. Whether you're building simple agents or complex multi-agent systems, Strands Agents provides the foundation you need to succeed in production.

Move AI agents from prototype to production faster. Whether you're using Strands Agents SDK, LangChain, or any other framework with your favorite LLM, AgentCore handles the infrastructure so that you innovate with confidence.

Join Swami Sivasubramanian, VP of Agentic AI at AWS, for a fireside chat exploring how organizations can successfully implement agentic AI. This Executive Summit session from AWS re:Invent 2025 covers identifying the right use cases to start with, understanding how agentic AI components fit together, navigating build-versus-buy decisions, and establishing trust as the foundation for AI adoption.

Everybody's talking about AI agents — but how do you actually build one? In this hands-on tutorial, you'll learn what makes up an AI agent (model, tools, system prompt, and the agentic loop) and then build your own from scratch using the Strands Agents SDK and Python. What you'll build: - A basic agent in 3 lines of code - Custom tools using the @tool decorator - A system prompt to shape agent behavior - An MCP server connection for real-world tool use Resources: Strands Agents: https://go.

The future of AI is multi-agent, and with Strands Agents 1.0, that future is ready for production. In this episode of "AWS Show and Tell - Gen AI", we'll guide you through building multi-agent applications using Strands Agents SDK. Strands Agents makes it easier than ever to build complex multi-agent systems that are reliable and production ready.

OpenAI open weight models now live on AWS! More AI choices than ever: • Expanded foundation model selection • Freedom to choose what fits your needs • Seamless integration with Amazon Bedrock & Amazon SageMaker JumpStart • World-class cloud infrastructure Pick your path to AI innovation with AWS! 🚀 #AWS #OpenAI #AI

Discover how organizations are transforming their businesses by truly making AI part of the team. Learn three key ways companies are putting AI to work today: revolutionizing business processes, reinventing the way individuals work and teams collaborate, and transforming customer experiences. We also explore how the future workplace will evolve as AI becomes an integral team member.

This video shows you how to use MCP servers with Strands Agents. It starts with a simple Strands agent, adds a tool, adds an MCP server, and then adds 3 MCP servers. Within minutes you will build an Agent that creates a step-by-step report on fine tuning Llama model using Amazon SageMaker AI with instance recommendation and pricing information - using 3 MCP servers.