Agentic AI Reference Architecture

Knowledge & Data · Data store

Personal Data Store

Data storeKnowledge & DataKnowledge & Dataarc:PersonalDataStore

A system-of-record database holding identifiable personal data about data subjects, such as customer, patient, employee or applicant records, processed by an application or AI system.

Responsibility. Persists identifiable personal data for its declared purposes.

Also known as: Customer database, Electronic health record, HRIS, Member claims store, User account database, Calendar, email, browsing, location, transaction and health data

emits telemetry tohas access controlled byis read byhas access controlled byis written byis written byis written byis read byis read byis constrained byis guarded byhas access controlled byis read byis written byis evaluated byis constrained byAudit Log Store: emits telemetry toAudit Log StoreAuthorization Policy Decision Point: has access controlled byAuthorization Policy Dec…Database Connector: is read byDatabase ConnectorIdentity Provider: has access controlled byIdentity ProviderErasure Orchestrator: is written byErasure OrchestratorData Retention Enforcer: is written byData Retention EnforcerData Subject Request Handler: is written byData Subject Request Han…User Need Predictor: is read byUser Need PredictorPersonal Data Exporter: is read byPersonal Data ExporterPersonal Data Retention Policy: is constrained byPersonal Data Retention …Protected Field Redactor: is guarded byProtected Field RedactorPurpose-Based Access Controller: has access controlled byPurpose-Based Access Con…Data Classifier: is read byData ClassifierField-Level Encryptor: is written byField-Level EncryptorPenetration Tester: is evaluated byPenetration TesterPurpose-Bound Data Schema: is constrained byPurpose-Bound Data Schema
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

emits telemetry to dynamic

has access controlled by control

is constrained by control

is guarded by control

is evaluated by assurance

Design guidance

Classification

Patterns
Integrity and confidentiality
Quality attributes
Privacy (NIST AI RMF: privacy-enhanced)Security (ISO/IEC 25010 | NIST AI RMF: secure and resilient)
Frameworks & regulations
GDPR Art. 32

Sources

  1. Ch9.7: T. Nguyen, "GDPR and Data Protection Regulations," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.7. ISBN: 9798244538229.
  2. Ch10.1: T. Nguyen, "Conversational UI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.1. ISBN: 9798244538229.
  3. Ch10.2: T. Nguyen, "Proactive Agents," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.2. ISBN: 9798244538229.
  4. Ref9.05: "Privacy and Data Protection for AI Systems," unpublished reference note (references/Chapter 9 - Safety, Ethics, and Compliance/05-Privacy-Data-Protection.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note