- Ignition: first start: 0/5
- Chassis: car + fuel: 0/4
- Lift and diagnostics: 0/3
- Fuel system: model gateway: 0/5
- Navigator: task route: 0/5
- Glovebox: context and memory: 0/4
- Rain sensor and wipers: pipeline: 0/5
- Hitch and roof rack: MCP, Hooks, Skills: 0/6
- Convoy: subagents and orchestration: 0/6 — now
- Road atlas: AI notebook: 0/5
- Dyno: engine tuning: 0/5
- Onboard computer: second brain: 0/5
You're building: Convoy: subagents and orchestration
Run it in your head — the last task where a single prompt turned out to be a blunt tool where you needed a crew.
Don't picture it as "a prompt that failed" — picture it as a heist that one person tries to pull off alone. Picking the lock, killing the cameras, driving the getaway car, and counting the loot, all at once. Something always drops. A professional crew splits the roles — every specialist covers their lane.
Replay it: how many "roles" did you end up juggling yourself — or forcing one prompt to juggle? Which link was the most fragile?
Getting it wrong is fine: it is part of learning. Guessing first helps the answer stick later, and the answer itself comes after the explanation.
Copy your personal prompt and paste it into your agent's learn mode — it picks up your context and takes you forward.
Honestly: with AI it feels like you can do more than you can without it. After practice, check yourself without AI. (Bastani et al., PNAS 2025)
Explains the material using the course method.