Agentic AI Reference Architecture

Safety & Security · Software component

PII Detector

Software componentSafety & SecuritySafety, Security & GovernanceVariation point (abstract)arc:PIIDetector

An abstract privacy component that locates personally identifiable information spans in document text and reports each with a PII type, detection method and confidence score.

Responsibility. Identifies personally identifiable information in content.

Also known as: PII detection

is invoked byis invoked byis invoked byis specialized byis specialized byis specialized byis specialized byis invoked byOutput Rail: is invoked byOutput RailInput Rail: is invoked byInput RailDocument PII Redactor: is invoked byDocument PII RedactorNER PII Detector: is specialized byNER PII DetectorPattern PII Detector: is specialized byPattern PII DetectorMulti-Strategy PII Detector: is specialized byMulti-Strategy PII Detec…Context-Aware PII Detector: is specialized byContext-Aware PII DetectorData Classifier: is invoked byData Classifier
Direct neighbourhood (hover for relationship types)

Variants

VariantWhen to choose
Context-Aware PII DetectorChoose for identifiers that are PII only in context (patient IDs, account numbers, internal IDs next to field labels).
Multi-Strategy PII DetectorChoose when documents mix structured, named and contextual PII (e.g., regulated healthcare content); avoids single-strategy blind spots.
NER PII DetectorChoose for unstructured PII such as person names, organizations and locations that regex cannot distinguish from normal text; costlier than patterns.
Pattern PII DetectorChoose for structured PII with predictable formats (SSNs, credit cards, phone numbers, emails); cheapest strategy but misses names and contextual identifiers.

Relationships

is invoked by dependency

Classification

Patterns
Confidence-scored detectionRegex plus named entity recognition
Quality attributes
Privacy (NIST AI RMF: privacy-enhanced)Transparency and accountability (NIST AI RMF: accountable and transparent)
Risks mitigated
PII entering the knowledge base and being surfaced in responses
Frameworks & regulations
HIPAA

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.
  2. Ch7.1A: T. Nguyen, "Advanced Implementation with Nvidia NEMO Framework and Nvlink," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1A. ISBN: 9798244538229.
  3. 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.
  4. Ref9.01: "AI Safety Frameworks for Agent Systems," unpublished reference note (01-AI-Safety-Frameworks.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note