Observe view, why-trace and item logs

The idea

A zoomable view over existing records goes from the fleet to a worker, a tool call and a delegation. It adds a 'why' timeline, a diagnostic bundle, the warn and error lines captured for each item, and front-door latency.

The problem
Debugging a worker meant reading the database by hand.
Why it matters
One connected view, with no execution model of its own and no writes on the hot path.
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

  • Worker Console tab

    Each AI worker's Console shows what it does now, what needs a person, a closed list of health checks with read times, and its history; a check failing 5 minutes opens an alert.

  • Native implementation round

    Implementation runs as one sandboxed Claude Code or Codex session, briefed by a compiled file. Its tools go through the gateway hook. The supervisor gets back only the report, the diff and the checks.

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.