The assignment
Build an interactive guide that teaches YOU Product Discovery.

A Lovable-hosted AI coaching tool that asks learners to submit their own product, audience, and problem, then returns AI-driven scoring and challenges on that input. The flow is staged, with an initial submission step followed by further coaching stages as the learner progresses.
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
What is not shown
Take this awayWorth opening if you are designing learning UX, then asking the question this build raises: what would make the learner commit to an answer before the app supplies one?
Discovery isn't a chapter you read — it's a muscle. The strongest builds here force a decision out of the learner, because the fastest way to internalise discovery vs. delivery is to practise the judgment call, not memorise the definition.
The learner has to make a call
The builds that landed put a decision in front of you — a scenario, a branching choice, feedback on your answer. The ones that didn't were articles with a nav bar.
Discovery vocabulary that holds up
Mom Test interviews, opportunity trees, riskiest-assumption tests, small prototypes shown to real users — the framing that separates discovery from delivery.
It teaches you, specifically
Your product as the worked example, your notes kept, your progress tracked. The brief said teaches YOU — and the generic explainers all read interchangeably.
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.