Autonomy modes and ask-for list

The idea

An org or worker picks Ask first, Auto or Full autonomy; risk tiers and a fixed ask-for list (merge, deploy, outside speech, spend, hiring, reorg, new integration) decide what waits for a person.

The problem
One fixed autonomy level is too loose for some teams and too strict for others.
Why it matters
Owners set how much the crew does before asking, per org or worker.
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

  • Approvals on web, WhatsApp, Slack and Teams

    A governed action waits for an approval that eligible people decide on the web, WhatsApp buttons or Slack/Teams direct messages; the requester never decides, and owned resources are approved by their owner.

  • Structured and plain-language policies

    Policies with worker > role > team > org precedence gate actions; a one-sentence rule drafts a policy with a preview, and free-text policies are read at the gateway where a model can only add an approval.

  • Everything is a setting

    Every default is a config key resolved from platform to org, department, worker and conversation, editable in the UI and API with its source shown.

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.