AI-Native Mentorship
AI-native mentorship, in the open.By Ankit Bhangar.
I mentor anyone changing how they work because of AI — product managers most of all — and the topics live here, free. Why a structured BRD matters more once a model is writing the code. How ChatGPT, Claude, Gemini and Perplexity compose into one method. And the everyday habits that change for everyone — like shipping a working website instead of a deck. No course, no cohort: read the topics, clone the repos, and bring the 1:1 when you want it.
- 01Public GitHub repos — real code, not theory.
- 02Passion-project energy — half-finished thinking, shared.
- 03BRDs still matter — more with AI in the loop, not less.
- 04Multi-model method — how ChatGPT, Claude, Gemini and Perplexity compose.
Threads worth pulling
Four ways in — a note, a case, a method, and a repo.
Latest note
All→Rules first, AI for the residual
On Podsque's completeness pipeline, deterministic rules filled ~70% of the gaps at zero cost and the model only handled the ~30% that needed judgment. Reach for AI on the part that's genuinely ambiguous, not the part you could just write down.
Featured case study
All→Making 'good answer' legible across four releases
FAQ answer quality across World Mobile releases was a matter of opinion until it had to be compared release over release. I used Claude with Harvey-ball scoring and narrative reasoning so 'this got better' became a defensible claim with editor-specific guidance — not a vibe.
Read the case →From the methodology
All→BRDs still matter — more, not less
The contrarian case: a structured requirements doc is the highest-leverage artifact you have once an AI is writing the code.
Read & try →Popular repo
All→