Agentic AI Reference Architecture

Observability & Evaluation · Data store

Centralized Log Store

Data storeObservability & EvaluationObservability & Evaluationarc:LogStore

A centralized, indexed store of structured log records from agents and inference services, queryable by field for troubleshooting and pattern analysis.

Responsibility. Retains searchable structured logs that explain why metric anomalies occurred.

Also known as: Searchable log index, Log backend, Log analytics platform

is monitored byreceives telemetry fromis read byis written byis read byis read byis constrained byPlatform Operator: is monitored byPlatform OperatorToken Cost Meter: receives telemetry fromToken Cost MeterIncident Manager: is read byIncident ManagerLog Aggregator: is written byLog AggregatorData Drift Detector: is read byData Drift DetectorOptimization Recommender: is read byOptimization RecommenderTelemetry Retention Policy: is constrained byTelemetry Retention Policy
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

receives telemetry from dynamic

is constrained by control

is monitored by assurance

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Patterns
Structured (JSON) loggingHot/archive log tiering
Technologies
ElasticsearchSplunkDatadogLokiAmazon S3 (archival)ELK StackNew Relic
Quality attributes
Maintainability (ISO/IEC 25010)Transparency and accountability (NIST AI RMF: accountable and transparent)
Risks mitigated
Undiagnosable latency and error spikesUndetected unauthorized access attempts

Sources

  1. Ch7.2: T. Nguyen, "Performance Optimization and Production Monitoring," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.2. ISBN: 9798244538229.
  2. Ch8.3: T. Nguyen, "Token Economics and Architecture," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.3. ISBN: 9798244538229.
  3. Ch10.4: T. Nguyen, "Human-in-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.4. ISBN: 9798244538229.
  4. Ref7.16: "Production Monitoring and Operations for Agentic AI," unpublished reference note (16-Production-Monitoring-Operations.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note
  5. Ref8.09: "Chapter 8 Summary: Run, Monitor, and Maintain," unpublished reference note (09-Chapter-8-Summary.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note
  6. Ref9.08: "Safety Incident Response for AI Systems," unpublished reference note (08-Safety-Incident-Response.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note
  7. Ref9.09: "Compliance Automation and Tools," unpublished reference note (09-Compliance-Automation-Tools.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note