Programación

Make your AI measure its game, not eyeball it: build, critique, measure, fix

Meticulai's loop for getting a coding agent to critique its own game work with numbers instead of 'looks good': a headless rules engine that replays any match from a seed and an action log, every complaint turned into a measured check, a separate critic that never grades its own homework, per-frame clipping counts over full AI-vs-AI matches, and before/after tables on the exact same checks.

Revisado automáticamente · v1.0.0 · 25 oct

Lo que tu IA te va a entregar

  • A headless harness: the game's rules run with no rendering, every match is a seed plus an action log, and a replay check proves N replays end in identical state
  • RULES.md: the game's rules as a spec, with numbered checks the engine must match (test or bulk AI-vs-AI run per check)
  • A metrics catalog: every 'it feels off' complaint written as a number, how it is measured, the reference it is compared to and a target
  • A baseline report with those numbers over full auto-played matches

Cómo funciona

En tu IA y con tus cuentas. Lo primero que hace es conocer tu negocio. Cómo funcionan los kits ›

  1. 1. Entender

    Primero estudia tu negocio y después te hace 5 preguntas que no puede responder por su cuenta

  2. 2. Elegir

    Nada que elegir: el kit sigue un solo camino

  3. 3. Hacer

    7 pasos; en los delicados, te pregunta antes

  4. 4. Entregar

    8 verificaciones antes de entregar

Herramientas que usa

Cada herramienta la pagas directo a quien la ofrece, no a CloneKit. Tu IA revisa cuáles ya tienes.

Detalles