> Agents playtest my games overnight I'm curious if you want to elaborate. What kind of games? Turn based? Do you just feed it repeated screenshots?

3D ARPG with dozens of systems, think Genshin or Fortnite. But it's all typescript running in the browser, so native browser introspection/debuggability came for free. The biggest problem TBH is the LLM thinking this is a web app, so it makes webby UIs that look out of place in the context of a game :D

Fable has a cromulent time building its own tests, tools and pipelines. But there's no magic, it literally uses the gamepad and plays the game itself, taking screenshots, profiling, and debugging as it goes. The game ticks are fully controllable so it can frame-advance at its own pace.

Sometimes I take screenshots if it's some very complex multi-step repro. But 90% of the time it drives the engine itself.