Fallback Chain Policy

Data artifactModel ServingModelsarc:FallbackChainPolicy

A priority-ordered list of alternative resources (primary provider, secondary provider on different infrastructure, cached results) that a router attempts in sequence when the preferred resource fails.

Responsibility. Defines the ordered fallback targets for a degraded resource.

Also known as: Fallback hierarchy, Provider priority list, Fallback tool chain, AI gateway fallback policy

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

Design guidance

SHOULD place a cached-result fallback last so that total failure is avoided even when all live providers fail.
SHOULD NOT place alternatives that share a failure domain (e.g., the same cloud availability zone) as the only fallback.
SHOULD list alternative tools (e.g., a secondary flight-search API with less complete data but higher availability) invoked when the primary tool fails after retries.
SHOULD ensure fallbacks actually solve the problem rather than mask failures.

Classification

Patterns: Fallback chainLast-resort cache fallback
Quality attributes: Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated: Undefined behaviour when primary provider fails

Sources

Ch2.8: T. Nguyen, "Error Handling and Resilience," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.8. ISBN: 9798244538229.
Ch3.7: T. Nguyen, "Tool Usage Auditing," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.7. ISBN: 9798244538229.
Ch4.2: T. Nguyen, "Deployment and Scaling," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.2. ISBN: 9798244538229.