Skip to main content

Scenario

An agent can execute production SQL changes. We require meaningful human verification with escalation on timeout.

Example App

Reference implementation: examples/openai-agents-change-control/
  • uses attesta_approval_handler
  • sets fail_mode: escalate
  • records audit evidence for each tool call

Core Pattern

Production Notes

  • route escalated outcomes into a ticketed out-of-band workflow
  • require change_ticket metadata for every destructive action
  • alert on repeated timeout escalations to detect approval-path drift