Overview
Your complete guide to AI agents
Two projects that turn a language model from a talker into a doer: a Python agent that picks its tools in a safe loop, then an MCP server that makes your tools available to any AI app.
Non-technical and technical learners alike. Every part opens two ways in: a plain path built on an analogy for someone starting from zero, and a detailed path for someone who knows the basics and wants depth.
An animation, then what you need before you start, then the idea with code you run, then a worked example, then review cards and "test your understanding" questions.
Do not leave a part before you can answer its questions without guessing. Reading alone proves nothing.
Pick a topic
A look at AI agents
You build the loop by hand first to understand what happens, then move the tools into a standard MCP server that works in any client.
| Part | Topic | You learn |
|---|---|---|
| 1 | Building an AI agent in Python | The agent loop, tool definitions, safety limits and stopping |
| 2 | Building an MCP server in Python | Tools, resources and prompts, JSON-RPC, and MCPServer |
Done with this lesson?
Sign in to save your progress.