Ten weeks
Core material ≈ 3.5 h each, then the build. Tick each week’s “Done when” list to track progress.
- Week 10/4
The Internals of Coding Agents
You build: A 300–500 line terminal agent with four tools and full logging
- Week 20/4
Advanced Context Engineering
You build: A one-page spec, one feature shipped through RePPIT, and an MCP server with 2–4 tools
- Week 30/4
Agent Skills and CLI
You build: A packaged skill with a helper script, plus a browser-driven web skill
- Week 40/4
Customizing Your Agent and Repository
You build: Repository instructions, two hooks, and a planner / implementer / reviewer split
- Week 50/4
Agent-Ready Codebases
You build: A scored readiness audit and the fixes that make a fresh agent productive
- Week 60/4
Agentic Code Review
You build: A severity-ordered review rubric wired to pull requests, measured on five PRs
- Week 70/4
Security
You build: A threat model, SAST / SCA / secret scans in CI, and a prompt-injection test
- Week 80/4
Background Agents
You build: An issue-to-PR flow with isolation, budgets, checkpoints, and retries
- Week 90/4
Building an AI-Native Team
You build: A model gateway, an MCP portal, and a one-page adoption policy
- Week 100/4
The Software Factory + The Future
You build: A traced end-to-end factory with an eval set and a controlled improvement loop