- Ignition: first start: 0/5
- Chassis: car + fuel: 0/4
- Lift and diagnostics: 0/3
- Fuel system: model gateway: 0/5 — now
- 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
- Dyno: engine tuning: 0/5
- Onboard computer: second brain: 0/5
You're building: Fuel system: model gateway
Picture your AI situation right now — budget, hardware, country, corporate restrictions.
Don't picture it as a "technical tool choice." Picture it as a mountain with two routes: the cable car and the hiking trail. Only you know what's in your pack, how much daylight is left, whether you need the summit today or just the panorama.
Run it in your head: which route feels like yours? Where is your "cable car" (fast, paid, convenient) — and where is your "trail" (slower, autonomous, yours)?
Which route fits your pack today?
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.