Human-in-the-Loop
Approval gates, risk assessment, escalation, confidence thresholds.
Between an agent proposing an action and executing it sits a risk assessment that routes high-impact actions to a human for approval — the architectural control that makes autonomous systems deployable.
Classify actions by reversibility and blast radius, preview them with dry-runs, design approval UIs that show what will actually happen, and audit every decision.
Human-in-the-loop blocks on approval; human-on-the-loop monitors and intervenes; both need escalation paths, SLAs and a defined fallback when nobody answers.
Model self-reported confidence is poorly calibrated; route to humans using external signals — evaluator scores, retrieval similarity, validation results — with thresholds set on eval data, not by feel.