Cognition · Software component

Plan Deviation Monitor

Software componentCognitionCognition & Memoryarc:PlanExecutionMonitor

An execution-monitoring component that compares primitive outcomes with operator-predicted effects and identifies the abstraction level whose assumptions failed.

Responsibility. Detects divergence between predicted and actual execution outcomes of a plan.

Also known as: Execution monitoring, Plan execution monitor, Discrepancy detector, Plan monitor, Plan Deviation Monitor

Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

Action Effect Model Ch5.6

invokes dependency

Tool Error Classifier Ch5.4

reads dependency

monitors assurance

Design guidance

MUST monitor primitive success and failure; primitives can fail despite satisfied preconditions (timeouts, rate limits, outages).
MUST run in parallel with execution and check preconditions before, progress during, and effects after each action.
SHOULD flag but not directly trigger replanning; severity evaluation decides whether a discrepancy warrants adaptation.
SHOULD also watch for goal changes, which invalidate plans through obsolescence rather than failure.

Quantitative guidance

As stated by the sources; verify before use.

Example: observed position 2.2 m from expected vs a 1 m verification tolerance (Ch5.6).

Classification

Patterns: Execution monitoringHierarchical replanning triggerPrecondition checkingProgress trackingEffect verificationExpected-vs-observed state comparison
Quality attributes: Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated: Assuming primitive tasks always succeedSilent plan invalidationAction execution failuresExogenous eventsSensor driftModel inaccuraciesGoal changes

Sources

Ch5.4: T. Nguyen, "Hierarchical Planning Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.4. ISBN: 9798244538229.
Ch5.6: T. Nguyen, "A* Search and Replaning," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.6. ISBN: 9798244538229.