[bashtoni]

Practically, what this boils down to is having clear success criteria.

The harness (Claude Codex, Codex, Pi etc) keeps throwing things into the context and executing tools (as directed by the model) until the success criteria is satisfied.

The "rules" of using AI successfully are basically just the rules of any successful development team. Break things down into clearly defined chunks, make the success criteria clear and provide a way to get the right feedback on how the system is running (logs, metrics, traces etc).