Agentic AI

This quickstart guide shows you how to create your first basic Strands agent, add built-in and custom tools to your agent, use different model providers, emit debug logs, and run the agent locally.

Learn from Spring AI-based Java code examples how to run Model Context Protocol (MCP) clients & servers on AWS, using Amazon Bedrock and Amazon ECS.

Learn how to use LangGraph and Mistral models on Amazon Bedrock to create a powerful multi-agent system that can handle sophisticated workflows through collaborative problem-solving.

Create your first AI agent using Strands Agents SDK and Amazon Bedrock with minimal code. Learn to set up your environment and build a subject expert agent as the initial step in our Integrated Learning Lab project.

Create your first AI agent using Strands Agents SDK and Amazon Bedrock with minimal code. Learn to set up your environment and build a subject expert agent as the initial step in our Integrated Learning Lab project.

Learn to connect your AI agent to the real world using built-in and custom tools. This tutorial explores Strands SDK's built-in tools and teaches you to create custom ones, transforming your conversational agent into a truly useful assistant.

Learn how to use different AI models with the Strands Agents SDK, including models from Amazon Bedrock and OpenAI, as well as local models with Ollama.

MCP is an open protocol that standardizes how applications provide context to large language models (LLMs), proposed by Anthropic. Acting as a universal connector for AI applications, it enables seamless integration between LLMs and various data sources and tools. AWS has joined the MCP steering committee and is excited to evolve the protocol together with the developer community.

In this video, Mike Chambers, Sr. Developer Advocate at AWS, explains the ins and outs of MCP. Explore how MCP decouples agents from servers, allowing for seamless integration with cloud-based resources and remote functionality.

Learn how AWS is enhancing the Model Context Protocol (MCP) for better agent-to-agent communication. Explore how features like human-in-the-loop, streaming results, and capability discovery are improving inter-agent collaboration.