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

AILingo is a 12-module Duolingo-style app for mastering LLMs, prompt engineering, RAG, and multi-agent workflows, playable as a guest with no signup required. Modules cover LLM basics (tokens, transformer foundations, temperature, text completion), prompt engineering, RAG systems, vector databases and embeddings, AI agents, fine-tuning (LoRA), memory and context, and evals and metrics. Progress is tracked with hearts, a day streak, and XP across a locked/unlocked module path, and the app fires live PostHog analytics events during normal use.
Kashish shipped a deployed web app you can open. This read comes from the artifact and Kashish's own account of it — no scores, just what the build does and does not show.
What it demonstrates
Take this awayTwo things travel from this build: short lessons beat comprehensive ones, and events defined before launch beat opinions formed after it.
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.