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

Tokenly is framed as ‘Learn AI like a PM,’ built from real workshop content. Its six micro-lessons cover what generative AI is, how LLMs predict the next token, tokens and context windows, vectors and embeddings, pre-training/RLHF/fine-tuning, and attention and hallucinations. Signing in saves progress and builds a streak, and the app loads PostHog's analytics SDK.
Niraj shipped a deployed web app you can open. Parts of it sit behind a sign-in, so this read leans on what is public plus Niraj's own description.
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.