- 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
- Road atlas: AI notebook: 0/5 — now
- Dyno: engine tuning: 0/5
- Onboard computer: second brain: 0/5
You're building: Road atlas: AI notebook → Road atlas
Take a rough count: how many hours of video are sitting in your "watch later" right now? A playlist of talks, a couple of lectures, something a friend sent with "you have to see this."
Now honestly: how much of it will you actually watch?
Picture a different deal. Same evening, same videos — but instead of a screen you have a digest. The key claims, the places where speakers disagree, and next to every claim a link to the exact spot where it was said. Not a retelling of who-knows-what, but a map with coordinates.
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.