This module is narrated by an AI voice model trained on Dr Ravichandran's own recordings — a real, working example of the AI-native approach this course teaches, not a shortcut around it.
What this module covers
Build a working, queryable knowledge base out of your own scattered decision history, and use it — through the frameworks from Modules 2–7 — to surface at least one real insight you'd otherwise have lost.
Framing
“The course closes with the single clearest insight the knowledge base itself surfaced when asked what mattered most across the whole three-year record: imperfect action with a modifiable product beats perfect planning without one.”
Build a working, queryable knowledge base out of your own scattered decision history, and use it — through the frameworks from Modules 2–7 — to surface at least one real insight you'd otherwise have lost.
Choose your track
Track A — Build it (technical / vibe-coded)
Replicate a lightweight version of the Module 1 pipeline on your own exported conversation history or documents, using free or low-cost tools. Run your build through the Module 6 risk checklist before submitting. Realistic time: 2–4 hours.
Track B — No-code equivalent
Achieve the same outcome — a personal, queryable knowledge base with semantic retrieval over your own material — using an existing tool that provides this out of the box. Realistic time: 45–90 minutes.
What you submit
- Proof the knowledge base exists and is queryable (a screenshot or short description plus one sample query and its result).
- Results from at least three queries run against it, each through a different module's lens, plus a short reflection on what surfaced.
- A one-page “what I'd do differently at scale” note.
Once you've worked through the capstone, mark it complete to leave feedback.