Retry Policy

Data artifactTools & IntegrationOrchestration & Toolsarc:RetryPolicy

A configuration artifact stating which error classes are retryable, the maximum attempts or per-node retry budget, base and maximum backoff delays, and jitter.

Responsibility. Specifies when and how often failed calls may be retried.

Also known as: Retry configuration, Retry budget, max_retries

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

is read by dependency

constrains control

Agent Controller abstract Ch3.8

Design guidance

MUST distinguish retryable from non-retryable error classes.
SHOULD bound retries per workflow node when retry loops are expressed in a state graph.
SHOULD cap retries (e.g., two attempts) before escalation and vary the approach rather than repeating identical failed calls.
SHOULD classify network timeouts, temporary unavailability and rate-limit-exceeded as retryable, and invalid tool names, missing credentials and malformed parameters as non-retryable.

Quantitative guidance

As stated by the sources; verify before use.

3-5 attempts; 60 s maximum delay (Ch2.8).
Batch ingestion retries up to 3 times with exponential backoff (Ch6.2B).
Exponential backoff example: wait 1 s, 2 s, 4 s ... up to a maximum delay (Ch6.3B).

Classification

Patterns: Exponential backoffJitterRetry budget per node
Technologies: LangChain AgentExecutorLangGraph
Quality attributes: Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)Performance efficiency (ISO/IEC 25010)
Risks mitigated: Wasted retries on non-retryable errorsInfinite retry loops

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.
Ch3.8: T. Nguyen, "Action Accuracy Metrics," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.8. ISBN: 9798244538229.
Ch6.2B: T. Nguyen, "Production Vector Database Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.2B. ISBN: 9798244538229.
Ch6.3B: T. Nguyen, "ETL Worked Example - Load Phase & Pipeline Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.3B. ISBN: 9798244538229.
Ch6.5: T. Nguyen, "Production RAG Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.5. ISBN: 9798244538229.
Ch8.2A: T. Nguyen, "Error Rates and Reliability," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.2A. ISBN: 9798244538229.