Show HN: Oneprompt – AI to go from problem description to MVP (experimental)(github.com)

  Problem mapping → personas → user interviews → vision → MVP scoping → user flows → architecture → scaffold → implement → polish → acceptance tests → persona usability testing → launch.

  Every stage produces a documented artifact. Every feature traces to a validated user need.

  The part I find most interesting: the personas created early in the process come back after the app is built and try to use it. They report what's broken or confusing, and fixes happen before launch. In practice this triggers multiple rounds
  of improvement and catches real UX issues.

  It generates Next.js/TypeScript apps. The whole methodology lives in one file. Repo includes an example run with all product artifacts and screenshots.

  https://github.com/geod/oneprompt