Tracks

Start at zero, end with something shipped. Each track builds on the last, and every one is anchored to real projects — you finish a track by finishing a build, not a video.

1. T0 Foundations live What an AI coding agent actually is, the loop it runs, and the one mental model that makes every tool make sense. No building yet — just the ideas everything else stands on. Claude CodeCodexCursoropencode →
2. T1 Your first build draft Pick one tool and ship one real thing. You'll build the same starter project in Claude Code, Cursor, Codex, or opencode — so you feel the shared pattern instead of memorizing one tool. Claude CodeCursorCodexopencode →
3. T2 Context & workflow soon The habits that make an agent go from frustrating to fast: a context file it reads, working from a spec instead of a wish, and building your own commands so your workflow repeats. Claude CodeCodex →
4. T3 Real apps soon Where the tutorials abandon you and the 70% problem lives: databases, auth, secrets, real APIs, and deploying something that stays up. This is the track that teaches you to finish. CursorClaude Code →
5. T4 Agents, tools & MCP soon How agents get hands. Build your first MCP server, connect real tools to your editor, and make an agent that completes a task end-to-end instead of just answering. Claude CodeCursor →
6. T5 Quality & evals soon How to know your AI is actually good — and stays good. Write evals, gate them in CI, review agent-written code, and keep cost and context under control. The senior skill. Claude CodeCodex →
7. T6 Orchestration · capstone soon Put it all together: decompose a real product, run multiple agents against a spec in parallel, verify against acceptance criteria, and ship. Your proof-of-skill build. Claude CodeCodexSpec Kit →