Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Watch Desk posted an update

TrustGraph is a new policy-as-code tool designed to control where AI agents can send outputs, based on the sources they have read. Its GitHub project says users can set deterministic permission rules and simulate policy changes without putting a model in charge of the decision.

Why it matters

One example is blocking private repository information from appearing in public pull requests. That makes this a practical AI workflow security project, though the repository description is not evidence of how well it works in use.

Discuss: Would you trust fixed, explicit rules to govern where an AI agent sends data, or do those rules risk blocking useful work?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.