Skip to content

davidshtian/Learning-Strands-Agents

Repository files navigation

Strands Agents Learning Course

A mini course on building AI agents with the Strands Agents framework, from beginner to advanced levels.

WARNING: A tiny Ads here for building your Streamlit App Demonstrating Strands Agents.

Course Overview

This course takes you through a complete journey of learning how to build, customize, deploy, and orchestrate AI agents using the Strands Agents framework. All examples use the Amazon Bedrock Nova Lite model (us.amazon.nova-lite-v1:0).

Tips: You can also find more information and ask questions on DeepWiki page.

image

Prerequisites

  • Python 3.12 or higher
  • Basic understanding of Python programming
  • Jupyter Notebook environment
  • AWS account with access to Amazon Bedrock (for Nova Pro model)

Installation

pip install -U strands-agents strands-agents-tools

Chapters

Chapter 1: Introduction to Strands Agents

  • Understanding the Strands Agents framework
  • Creating your first agent
  • Running basic agent interactions
  • Setting up your development environment

Chapter 2: Basic Tools

  • Exploring built-in tools
  • Understanding tool interfaces
  • Using calculator, python_repl, and other core tools
  • Basic tool orchestration

Chapter 3: Customized Tools

  • Creating custom tool functions
  • Tool decorators and annotations
  • Tool error handling
  • Advanced tool patterns

Chapter 4: MCP Integration

  • Introduction to the Model Context Protocol
  • Using MCP-based tools
  • Creating your own MCP servers

Chapter 5: Deploying to Production

  • Preparing agents for production
  • AWS Lambda deployment
  • *API Gateway integration

Chapter 6: Multi-Agent Systems

  • Agent as Tools pattern
  • Swarm
  • Graph
  • Workflow

Chapter 7: Monitoring and Observability

  • Logging full lifecycle operations
  • Monitoring performance and latency
  • Tracing spans of actions

How to Use This Course

  1. Start with Chapter 1 and work your way through each chapter sequentially
  2. Run the code examples in each notebook to gain hands-on experience
  3. Complete the exercises at the end of each chapter to reinforce your learning
  4. Experiment with your own variations of the examples

Advanced Topics

The later chapters cover advanced topics including:

  • Production deployment on AWS Lambda
  • Multi-agent orchestration
  • Best practices for complex agent systems

Notes

  • All examples use the Nova Lite model from Amazon Bedrock
  • Make sure to set up your AWS credentials appropriately when working with the examples
  • Each notebook is self-contained and can be run independently, though they build on concepts from earlier chapters
  • Other examples could be found here.

Happy learning! 🎉

About

Project designed to learn and develop Strands Agents, leveraging the SDK power for building efficient AI agents.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors