Governance & Compliance · Data artifact
Approval Timeout Fallback Policy
Data artifactGovernance & ComplianceSafety, Security & GovernanceVariation point (abstract)arc:ApprovalTimeoutFallbackPolicy
An abstract policy setting the automatic outcome when no approver in the escalation chain responds before the final deadline.
Responsibility. Determines the terminal disposition of expired approval requests.
Also known as: Final escalation fallback
Variants
| Variant | When to choose |
|---|---|
| Auto-Approve Timeout Fallback | Choose when actions are reversible and organizational risk tolerance favors velocity over oversight (aggressive). |
| Auto-Reject Timeout Fallback | Choose when actions are irreversible or risk tolerance is low (conservative; prevents unauthorized actions). |
| Escalate-Up Timeout Fallback | Choose when the decision must still be made promptly and higher authority is available to make it. |
| Post-Hoc Review Timeout Fallback | Choose for time-critical decisions whose delay harms users (e.g., emergency claims or treatments) when approval queues exceed their SLA. |
| Retry-Queue Timeout Fallback | Choose when the request remains valid later and neither declining nor escalating further is appropriate. |
Relationships
configures structural
Design guidance
- SHOULD choose the fallback according to action reversibility and organizational risk tolerance.
- MUST define explicitly what the agent does when human response misses its response-time SLO, rather than leaving the agent in an ambiguous waiting state.
Sources
- Ch9.2: T. Nguyen, "Action Constraints and Permission Models," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.2. ISBN: 9798244538229.
- 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.
- Ch10.5: T. Nguyen, "Human-over-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.5. ISBN: 9798244538229.