Agentic AI Reference Architecture

Orchestration · Software component

Stalled Workflow Resumer

Software componentOrchestrationOrchestration & Toolsarc:StalledWorkflowResumer

A monitoring function that detects agent workflows left incomplete by function timeouts or interruptions and resubmits continuation events that resume them from the last checkpoint.

Responsibility. Restarts interrupted workflows from their last checkpoint.

Also known as: Continuation monitor

monitors; triggersreadsdeployed onEvent-Triggered Agent: monitors; triggersEvent-Triggered AgentState Checkpoint Store: readsState Checkpoint StoreServerless Function Runtime: deployed onServerless Function Runt…
Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

reads dependency

triggers dynamic

monitors assurance

Classification

Patterns
Checkpoint-and-continue
Quality attributes
Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated
Workflows exceeding platform timeout limitsLost progress after interruption

Sources

  1. 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.