Agentic AI Reference Architecture

Observability & Evaluation · Software component

Corpus Drift Detector

Software componentObservability & EvaluationObservability & Evaluationarc:CorpusDriftDetector

A monitoring component that tracks statistical characteristics of the knowledge corpus over time and flags significant changes that may indicate emerging data-quality issues.

Responsibility. Detects drift in corpus characteristics in production.

Also known as: Drift detection, Data drift monitor

sends data tomonitorsAlert Manager: sends data toAlert ManagerVector Index Store: monitorsVector Index Store
Direct neighbourhood (hover for relationship types)

Relationships

sends data to dynamic

monitors assurance

Classification

Patterns
Continuous quality monitoring
Quality attributes
Maintainability (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated
Gradual quality decay as sources evolve and the corpus ages

Sources

  1. Ch6.4: T. Nguyen, "Data Quality Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.4. ISBN: 9798244538229.