Enables AI coding agents to evaluate actions against team-defined policies, record decisions, and obtain human approvals for potentially risky operations.
Human approval for AI agents: request_human_approval pauses a high-stakes action until a named person approves or rejects (console, email, Telegram, Slack); silence is not consent. Every decision is sealed in a hash-chained audit log. EU-hosted.
Enables AI agents to safely execute privileged commands by routing them to a human approver, who runs them outside the agent's context and returns the output to the model.