The assignment
Build an app that makes you learn AI concepts the Duolingo way. Wire it up with PostHog for analytics.

AI Academy is built around the thesis ‘Don't learn AI concepts. Build AI products — then learn why they work.’ It's organized into worlds and missions, each following a five-step lesson flow (Challenge, Guided Build, Exercise, Artifact, Reflection) covering practical AI-building skills like prompt engineering, building a RAG pipeline, an eval harness, and agent loops. The app includes multiple sections — Home, Learning Paths, Playground, Skill Graph, AI Coach, and Analytics — and tracks levels, XP, and a streak counter with per-mission XP rewards.
Baskar shipped a deployed web app you can open. This read comes from the artifact and Baskar's own account of it — no scores, just what the build does and does not show.
What it demonstrates
Take this awayCopy the discipline more than the curriculum — instrument on day one. Shipping without analytics makes your next iteration a guess.
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.
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.