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 Prachi shipped
ALTA — ‘Learn AI. Grow Higher.’ — is an installable progressive web app offering daily AI product-management practice for PMs. Its curriculum covers tokens, embeddings, vectors, attention, hallucination, context windows, fine-tuning, RLHF, and transformers, delivered through case studies, an interview-practice mode, and a ‘war room’ scenario feature. Progress is tracked through streaks, unit checkpoints, a capstone project, and downloadable lesson-completion cards, with PostHog instrumentation capturing lesson starts, completions, and other learning events throughout the app.
✳Our read on this build
Prachi shipped a deployed web app you can open. This read comes from the artifact and Prachi'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, a daily goal and bite-sized lessons — the mechanics that make a habit instead of a bookmark.
- The syllabus is the real vocabulary — tokens, embeddings and attention — not a tour of how AI is changing everything.
- PostHog and event tracking appears in the shipped product — the tell of a builder who wants to know how it is actually used.
Take this awayCopy the discipline more than the curriculum — instrument on day one. Shipping without analytics makes your next iteration a guess.
✳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.