Tag: Claude Code hooks
-
Agentic AI Audit Trail: Log the Handoff, Not the Answer
What is an agentic AI audit trail? An agentic AI audit trail is the harness’s record of every handoff, every tool call and every gate decision. The harness writes it, not the agent. It answers one question after the fact: who did what, on whose brief, and what did they see. So when the orchestrator…
-
Agentic AI Human-in-the-Loop Gate: Gate What Matters
What is an agentic AI human-in-the-loop gate? An agentic AI human-in-the-loop gate is a checkpoint in the harness. It pauses one class of agent action until a named person approves it. The gate sits on the action, not on the prompt. So it fires only when the agent tries to do something that matters. New…