Agentic AI Reference Architecture

Safety & Security · Software component

Semantic Compliance Classifier

Software componentSafety & SecuritySafety, Security & Governancearc:SemanticComplianceClassifier

A domain compliance rail that uses semantic similarity models to detect regulated intent, such as advice giving, independent of surface wording.

Responsibility. Detects paraphrased regulatory violations by semantic intent.

Variant of Domain Compliance Rail abstract

When to choose. Choose when adversaries or the model paraphrase regulated content, so advice-giving intent must be detected regardless of phrasing, accepting higher false positives and compute cost.

specializesis target of alternativeToDomain Compliance Rail: specializesDomain Compliance RailPattern Compliance Checker: is target of alternativeToPattern Compliance Checker
Direct neighbourhood (hover for relationship types)

Relationships

alternative to variability

Classification

Patterns
Semantic similarity detection
Risks mitigated
Paraphrased investment adviceSubtle market manipulation languageCoded discriminatory lending terms

Sources

  1. Ch9.1: T. Nguyen, "Output Filtering and Content Moderation," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.1. ISBN: 9798244538229.