Shadow first, promote on measured outcomes

The idea

A new decision point starts in shadow. It is scored offline on labelled cases and live on outcomes, then promoted or demoted on that evidence. It acts only on the answer keys measured safe.

The problem
A decision model that nobody measured could act wrongly at scale.
Why it matters
A purpose acts only after this organization's own data shows it is right, and it drops back when misses rise.
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.

  • System One decision cascade

    Bounded choices (route, next action, failure class, done, risk, intent) are typed questions. A rule answers first, then a typed arm, then a small LLM, each with a confidence.

  • Adaptive per-turn context

    Typed decisions say which optional sections a turn needs and how to retrieve. Code plans the slots under a ceiling, with a reduction ladder that never cuts more than before, and limits the queries.

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.