Four outcome-per-module courses that ship with real infrastructure — learn in class, then keep the workspace running while you build your own thing.
Every course is an outcome with a spec sheet — not a slide deck. You finish with something real that keeps running.
Take a fuzzy feature request from idea to merged PR in one focused 30-minute loop — prompt, plan, code, review, ship.
Architect a swarm of specialist agents that collaborate over a custom MCP server — and orchestrate them with Way of Teams.
Design, build, test, and publish a production-grade ai-harness skill — bundled, documented, and deployed to the registry.
Stand up your own production workspace — repo mounts, encrypted keys, OpenChamber, and a real deploy loop — then scale it for a team.
None — a browser and an idea are enough.
CRS-100 or prior agent-hands experience.
CRS-200 recommended (MCP fluency helps).
Any prior course. Bring a repo you want to ship.
Every module runs in a live OpenChamber sandbox with the toolchain pre-configured. You type real commands and watch real agents work.
Lessons are orchestrated by a specialist agent swarm that plans, codes, reviews, and evaluates — exactly what you'll learn to control.
The workspace and skills you build stay yours after the course ends. It's your factory warm-up, not a demo.
"I shipped my first skill before the intro was over. CRS-300 is a cheat code."
"CRS-200 changed how I think about agents — it's roles and handoffs, not magic."
"The 30-minute clock is the single best habit I've picked up in years."
No. Every course is hands-on but zero-friction: you get a shared OpenChamber sandbox that already has the toolchain configured, so you learn by running real commands, not by reading slides.
Cohort caps keep the pairing honest — 40 builders for workshops, 30 for skills. Get on the Discord to lock your seat before the list fills.