Weeks 1–3 gave you every primitive: the agent loop, tools, evals, streaming, RAG, durable execution, sandboxing, human approval. Starting now, you stop building exercises and start building a product — a working clone of a professional AI coding agent, one subsystem per week.
By Week 12 it reads codebases, edits files, runs commands, plans, remembers, previews artifacts, traces itself, and orchestrates sub-agents. It goes in your portfolio, not in a folder of course exercises.
And we are not designing in the dark. This course uses the actual Claude Code source as a reference implementation. Each week, after building our own version of a subsystem, we open the real thing and study the decisions a production team made.
Why start with the interface? Because the interface is the product. An agent that thinks brilliantly but dumps a wall of text after forty silent seconds feels broken.
The walkthrough
Each part adds one capability to the same growing codebase, and each is a runnable checkpoint.
- 01The REPL skeletonA read-eval-print loop that feels instant and never blocks on a long model call.
- 02Streaming outputTokens as they arrive, so the machine visibly thinks out loud.
- 03Slash commandsAn escape hatch for everything that is not a model turn.
- 04Safe interruptsCtrl-C that cancels the turn without corrupting the conversation state.
- 05The cost meterLive token and dollar accounting, because the bill is a feature.
After this week you can
- Build a responsive streaming terminal interface
- Handle cancellation without losing conversation state
- Track and display real-time token cost