Evidence-gated questions and settled decisions
The idea
A blocking question is refused until research cites a tool result, and asking again about a settled decision needs new evidence. A decision that arrives after a completion claim sends the work back.
- The problem
- Workers asked people things that research or earlier answers had already settled.
- Why it matters
- People get fewer needless questions, and reviewers know what people decided.
- Where it stands
- In production as of
A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.