Twenty-one modules take you from "what is a token?" to agents, MCP servers, skills, RAG, evals, security and leading your team's adoption. Each one explains the idea plainly, shows it moving step by step, gives you a memory hook, and has you try it in all five major tools: Claude Code, Antigravity CLI, GitHub Copilot, Cursor and Codex.
Every module has the same ten sections, so you always know where to look:
An everyday analogy and a plain explanation, a flow diagram and step-through player, then an interactive widget to try it yourself.
Why it matters in real work, and exactly where the idea shows up in Claude Code, Antigravity CLI, Copilot, Cursor and Codex.
A memory hook with a full explanation, common mistakes, a 20–30 minute hands-on lab, a quiz, and the best free resources to go deeper.
A real repository, anonymised, set up so an AI agent can work in it reliably: what lives in instructions, skills, scripts, hooks and human review, and how to decide.
Thirty minutes a day, five days a week. Each week covers one module (or practises one), using the daily rhythm on the Start here page: learn on Monday, build in one tool on Tuesday, repeat in a second tool on Wednesday, read what changed on Thursday, and explain it in your own words on Friday.
| Week | Module | Practice output by Friday |
|---|