Governed outreach to outside people

The idea

Workers contact prospects, customers and partners only through one gate that checks consent, limits, sending hours and content, and asks a person before a first contact.

The problem
Unchecked outbound messages risk spam and harm.
Why it matters
Outside contact is consented, limited and approved.
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

  • AI receptionist for unknown senders

    With public inbound on, an unknown WhatsApp or SMS sender or caller gets a fixed-template reply and each message becomes a Flow signal; asking for a person notifies the owner.

  • The closed list

    Only seven decisions reach a person (customer release, spend over the ceiling, outside credentials, outside contact, policy exception, reversing a person's decision, legal matter), detected from structure; the rest settle inside the org on record.

    Recorded walkthrough

  • Gate on all outgoing text

    Commits, PR text, comments, messages and reports go through rule-based checks (length, structure, banned phrases, attribution, secrets) and a style check against examples a person approved. Failing text gets a limited number of rewrites.

  • 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.

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.