- 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 — now
- 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: Rain sensor and wipers: pipeline
💡 Stack-agnostic. This module uses Claude Code as a case study: the built-in WebFetch tool reads the page, then comes the analysis. In other stacks the pattern is the same: you need any page-reading tool your agent has (built-in or an MCP server, module 07). See module 03 for your stack.
Catch one cycle from the last three days: you pulled something from the internet and delivered it somewhere else.
Don't picture it as "working at a computer." Picture it as a factory assembly line. The part (information) lands on the belt, passes station to station (read, extract, relay), and exits as a finished product at the other end.
Run that line in your head: how many stations? At which one does the belt slow down and a backlog starts forming?
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.