Human Oversight · Data artifact
Approval SLA Policy
Data artifactHuman OversightExperience & Human Oversightarc:ApprovalSLAPolicy
A configuration of maximum acceptable human-approval times per urgency class, together with the actions taken on breach such as parallel routing to backup approvers, pool expansion or incident response.
Responsibility. Defines approval-time objectives by urgency and the responses to their violation.
Also known as: Approval SLAs, Time-bounded decision policy, Response window
Relationships
configures structural
Design guidance
- MUST bound every approval with a response window so requests never wait indefinitely.
- SHOULD treat SLA violations as incidents signalling capacity shortfalls, not as inevitable operating characteristics.
Quantitative guidance
As stated by the sources; verify before use.
- Example SLAs: routine requests within 2 hours, standard within 24 hours, complex cases within 72 hours (Ch10.4).
- Timeout policies typically enforce 24-72 hour response windows before timeout escalation (Ch10.4).
- Ref10.01 workflow timeouts: simple approval 5 minutes, collaborative refinement 30 minutes, expert escalation 2 hours.
Classification
- Quality attributes
- Performance efficiency (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
- Risks mitigated
- Indefinite waits on human approvalExtended approval delays harming users
Sources
- Ch10.4: T. Nguyen, "Human-in-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.4. ISBN: 9798244538229.
- Ref10.01: "Human-in-the-Loop Systems for Agent Interactions," unpublished reference note (01-Human-in-the-Loop-Systems.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note