Observability & Evaluation · Software component

Dependency Health Monitor

Software componentObservability & EvaluationObservability & Evaluationarc:DependencyHealthMonitor

A monitoring component that checks the availability of an agent's downstream dependencies (LLM providers, rule engines, external APIs) so degradation decisions reflect current component health.

Responsibility. Detects failures of downstream dependencies at runtime.

Also known as: Component health checks, Latency anomaly detection

Direct neighbourhood (hover for relationship types)

Relationships

is invoked by dependency

Health Check Aggregator Ref8.07

sends data to dynamic

triggers dynamic

Alert Manager Ref8.04

monitors assurance

External Service API Ch2.8 Ch3.7 +2
LLM Inference Service Ch2.8
Rule-Based Analyzer Ch2.8
Tool Integration Adapter abstract Ref8.07
Vector Index Store abstract Ref8.07

Design guidance

MUST be in place for graceful degradation to detect which components have failed.
SHOULD monitor tool latency distributions over time to detect rate limiting, service degradation or network problems before complete failures occur.
SHOULD probe every tool and memory store (knowledge base count, vector search, long-term memory load) as part of integration health.

Quantitative guidance

As stated by the sources; verify before use.

Example: a payment tool's p95 latency rising from 800ms to 5s within an hour signals provider issues even though requests eventually succeed; typical 500ms calls suddenly taking 10s indicate throttling or degradation (Ch3.7).
Baseline: > 98% success for critical tools, p95 latency < 2 s, < 5 rate-limit incidents/hour, < 1% timeouts; alert on success < 95%, average latency > 5 s or > 10 rate-limit hits (Ref8.04).

Classification

Patterns: Health checking
Quality attributes: Maintainability (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated: Undetected component failure cascading into total failureUndetected rate limiting or provider degradation before complete failure

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.
Ch8.2B: T. Nguyen, "NeMo Guardrails Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.2B. ISBN: 9798244538229.
Ref8.04: "Data Quality and Drift Detection for Agent Systems," unpublished reference note (04-Data-Quality-Drift-Detection.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note
Ref8.07: "Agent Health Checks and Diagnostics," unpublished reference note (07-Agent-Health-Checks-Diagnostics.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note