Human-in-the-Loop as Architecture
Human-in-the-loop as a first-class architectural decision. Approval gates, escalation policies, audit logging, and the Incident Runbook Agent.
HITL done poorly is worse than no human at all. It creates the appearance of oversight without the substance. This chapter treats human-in-the-loop as a first-class architectural concern, not an afterthought.
What this chapter covers
- The three primitives — approval gates, escalation policies, audit trails
- Design guidance — structuring when and how humans intervene
- The working example: Incident Runbook Agent — multi-agent with human approval before remediation
- When HITL is security theater — rubber-stamping vs real oversight
- Cost of HITL vs value of HITL — the tradeoff analysis most teams skip
- Building for auditability — decision trails useful for debugging, compliance, and improvement
- Failure modes — what breaks in human-agent interaction
Code companion
The working code for this chapter is in src/ch05_hitl/:
approval.py— Approval gate implementationescalation.py— Escalation policy engineaudit.py— Audit logging system
Get the full chapter
The complete chapter text is available in the book.