Agentic AI Reference Architecture

Safety & Security · Software component

Context-Aware PII Detector

Software componentSafety & SecuritySafety, Security & Governancearc:ContextAwarePIIDetector

A PII detector that uses document structure and keyword proximity to field labels to classify otherwise generic values, such as numbers labelled 'Patient ID', as PII.

Responsibility. Detects values that become PII through their labelling context.

Also known as: Context-aware detection, Keyword proximity detection

Variant of PII Detector abstract

When to choose. Choose for identifiers that are PII only in context (patient IDs, account numbers, internal IDs next to field labels).

alternative tospecializesalternative tois invoked byNER PII Detector: alternative toNER PII DetectorPII Detector: specializesPII DetectorPattern PII Detector: alternative toPattern PII DetectorMulti-Strategy PII Detector: is invoked byMulti-Strategy PII Detec…
Direct neighbourhood (hover for relationship types)

Relationships

is invoked by dependency

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Classification

Patterns
Keyword proximity analysis
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Exposure of medical record and account numbers

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.