Part 2 — For the Developer
Ch. 16 — Human-in-the-Loop — When Agents Must Stop and Ask
Designing escalation and approval flows — the engineering patterns that keep humans appropriately in control.
Human oversight is not a UX preference in agentic systems. It is a compliance requirement that must be engineered in, not bolted on.
An agent that processes a loan application, generates a clinical recommendation, or terminates an employment contract is making a consequential automated decision. The frameworks are explicit about what that requires:
These are not preferences. They are architectural constraints. If a human cannot see what the agent is doing, intervene before or after the fact, and contest its decisions, the system is non-compliant by design.
Platform Agentic
Compliance, governance, and accountability for teams building agentic AI systems.