A Claude-built browser game teaches the EU AI Act

fixai.dev is a for learning the through simulated disputes with . The player receives a negative AI decision, such as denied insurance coverage, a rejected mortgage, or a high-risk label from . The player has only a few messages to push back, and success depends on citing the right legal article.

Eleven new levels cover banned uses such as workplace emotion recognition and social scoring, high-risk AI decisions in credit, hiring, and medical triage, and failures to explain AI decisions clearly. The main build challenge was making Haiku act like a stubborn company bot while still responding correctly when the player cites articles such as Art. 5 or Art.

86. If the bot is too strict, the game feels unfair; if it is too forgiving, the challenge disappears. The app uses and , was built with Claude, and works without an account.

Key points

  • fixai.dev teaches the through a .
  • Players challenge AI decisions by citing the correct legal article.
  • The new levels cover banned AI uses, high-risk decisions, and failures.
  • Haiku is tuned to behave like a stubborn company bot while still recognizing correct legal citations.
  • The project uses and , was built with Claude, and needs no account.
Read original