Flow signal triage

The idea

Ideas, requests and problems arrive as signals. Rules decide each signal at once, using the triage employee's accepted lessons, while System One is measured next to them. Each decision becomes held work or started work.

The problem
A person had to sort incoming requests before anything happened.
Why it matters
Each signal is decided in seconds without a model, and a person's decision always wins.
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.

Where it lives in the product

  • A person or one employee owns pipeline stages

    Plan, build, verify and deploy stages each have an owner; a person owner must approve or send back before work passes, and setup can make one AI employee responsible for all four.

  • 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.

  • Health components and incident watch

    Each module registers its own health checks, and /_health never calls a paid provider. A required component that fails past a grace period is filed once as an incident.

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.