Self-Improving Agent Workshop
Build a self-extending, self-modifying, autonomous agent and deploy it (6 steps, AIM308)
Examples
Explore complete examples, organized by what you want to learn or build.
Learn
Guided projects for learning advanced Strands patterns.
Streaming Express Chatbot with MCP
Express chatbot with SSE streaming, Zod tools and MCP
Deploy
Take Strands applications from local development to production.
A2A Shopping Assistant on AgentCore
This tutorial demonstrates how to use the Strands Agents SDK to build and deploy a multi-agent system on Amazon Bedrock AgentCore. You will create three specialized agents, each running in its own managed runtime, that discover and…
Next.js Chat App with Vercel AI SDK
Next.js chat app: Vercel AI SDK client + Strands server via the VercelModel adapter
Industry use cases
Apply Strands to real operational and business workflows.
AWS Lambda Failure Analysis Agent
Event-driven Lambda error diagnostics using CDK, EventBridge, and Bedrock Knowledge Base RAG for root cause analysis with confidence scoring
Technical use cases
Solve common engineering problems with complete Strands implementations.
Production Agent API with FastAPI
A single runnable Python service, in the shape of a benchmark chatbot repo (FastAPI, three tools, one model call), rebuilt on Strands Agents. It wires the production concerns you actually ship with: an OpenAI or Bedrock provider, max…
Book Renewal Agent: Control Strategies
Demonstrates different approaches to controlling AI agent behavior with a librarian agent. Users can chat with the agent, ask questions, and request to renew a book.
Red-Team a Refund Agent
This sample red-teams a small returns-desk agent for a made-up shop, Tidewater Outfitters, built on Strands Agents. The attacks come from the red-teaming feature in Strands Evals 1.7.0. The point of the sample: an eval's score and the…
User experiences
Build interactive agent interfaces and human approval flows.
Human-in-the-Loop Order Approval
An order approval system that demonstrates human-in-the-loop workflows using Strands Agents' interrupt/resume pattern. A multi-agent graph evaluates incoming orders — assessing risk factors like customer history, order value, and…
Agent-Generated Workout Tracker UI
An agent that chooses which UI components to render and reacts to form and button interactions