Agentic AI Reference Architecture

Observability & Evaluation · Data store

Data Validation Result Store

Data storeObservability & EvaluationObservability & Evaluationarc:DataValidationResultStore

A persistent store of structured per-document validation results (field, severity, message, source) retained for auditing, failure-pattern analytics and trend analysis.

Responsibility. Persists validation outcomes for audit and quality trend analysis.

Also known as: Validation result persistence, Validation report store

is read byis read byis read byis written byis written byis written byAlert Manager: is read byAlert ManagerMetrics Dashboard: is read byMetrics DashboardSLO Monitor: is read bySLO MonitorData Quality Validator: is written byData Quality ValidatorIndex Integrity Validator: is written byIndex Integrity ValidatorReferential Integrity Validator: is written byReferential Integrity Va…
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

Design guidance

Classification

Patterns
Structured error reporting
Quality attributes
Transparency and accountability (NIST AI RMF: accountable and transparent)Maintainability (ISO/IEC 25010)
Risks mitigated
Undiagnosed systematic source failures (e.g., a broken API corrupting dates)

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.