runestone labs gatekeeper
Early access

WRITING

Notes on agent policy and enforcement.

Short, specific, opinionated. No "AI safety" handwaving.

Subscribe · RSS
· policy, approvals, architecture

Allow, approve, deny — why binary policy fails for AI agents

Allow/deny is why people disable security tools. A third decision — pause for human approval — is the difference between a policy engine you leave on and one you wrap in try/except.