Easier to read with cream paper, a tint, more contrast or larger text? Choose your colours and text, once, for every page.

Free module

Building agents

Learn building AI agents hands on: plan and stop a run, give it memory, hand work between agents, checkpoint it and speak MCP.

6 lessons380 min lessonSoftware engineering

The lessons

Each lesson is free to read in full. Create a free account to run its commands in a live lab and to sit its quizzes and tasks.

  1. 1 · Container lab

    How to plan and stop an AI agent

    I can make an agent plan its steps and stop on a rule.

    Read the lesson

  2. 2 · Container lab

    How an AI agent remembers

    I can decide what an agent remembers between steps and between runs.

    Read the lesson

  3. 3 · Container lab

    Multi-agent systems and hand-offs

    I can split work between agents and say when one agent is enough.

    Read the lesson

  4. 4 · Container lab

    Checkpoints for long-running agent work

    I can make long work safe to stop and resume.

    Read the lesson

  5. 5 · Container lab

    MCP by hand: JSON-RPC over stdio

    I can read and write the messages a tool server and its client exchange.

    Read the lesson

  6. 6 · Container lab

    Build a small AI agent in Node

    I can build a small agent that plans, calls tools, remembers and stops.

    Read the lesson

Worked in a real lab

Every lesson of this module is worked in a lab started for you alone. The labs it uses:

Teaching a class? Set this module for your students with a teacher guide, marked assignments and a lab for every student.