Duolingo-style AI concepts learner
The assignment
Build an app that makes you learn AI concepts the Duolingo way. Wire it up with PostHog for analytics.
✳What Shohan shipped
PM Learner is a Duolingo-style skill-path app covering product management fundamentals across six units: Value Architecture and Product Sense/PMF, Continuous Discovery and the Mom Test, Product Strategy, Collaborative Execution, Technical Leverage (AI & APIs), and Executive Storytelling. It includes hearts, a streak counter, XP, a leaderboard, and sequential lesson locking/unlocking, along with a labeled ‘Active Case’ scenario feature.
✳Our read on this build
Shohan shipped a deployed web app you can open. This read comes from the artifact and Shohan's own account of it — no scores, just what the build does and does not show.
What it demonstrates
- The return loop is real: streaks, XP and bite-sized lessons — the mechanics that make a habit instead of a bookmark.
What is not shown
- The concepts covered are not listed publicly, so how far past 'what is AI' this goes is unclear from outside.
- No analytics wiring is visible in what is public, so how the app is really used stays unknown — including to its builder.
Take this awayA solid look at gamified learning UX; the sharper question is which event you would need to see to know which lesson people quit on.
✳Why this quest matters
Retention is a design problem, not a content problem. Wiring PostHog in from day one is the tell of a builder who ships to learn from real behaviour — rather than to admire their own screenshot.
✳What separated the strongest builds
A loop worth coming back to
Bite-sized lessons, instant feedback, and a reason to return tomorrow — streaks, XP, spaced review. A long article with a quiz at the end is not the Duolingo shape.
Concepts that are worth the streak
Tokens, embeddings, attention, hallucination, RAG — the vocabulary a PM needs in a real conversation, not 'what is AI' trivia.
Instrumented, not just launched
PostHog wired in and firing real events. An analytics claim nobody can verify tells a reader nothing about how the product is used.
No numeric scores are published here. These pages are written reads of what each builder shipped — the build is the point, not a mark out of a hundred.