Agentic AI Reference Architecture

Safety & Security · Software component

Moderation Inference Service

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

An abstract service that executes content-classification inference for moderation filters and returns category scores.

Responsibility. Serves content-moderation classification requests.

is invoked byis specialized byis specialized byToxicity Classifier: is invoked byToxicity ClassifierThird-Party Moderation Service: is specialized byThird-Party Moderation S…Self-Hosted Moderation Service: is specialized bySelf-Hosted Moderation S…
Direct neighbourhood (hover for relationship types)

Variants

VariantWhen to choose
Self-Hosted Moderation ServiceChoose when lower latency is needed and content must not be exposed to third parties (critical for HIPAA or GDPR), and ML infrastructure expertise is available.
Third-Party Moderation ServiceChoose when ease of integration outweighs dependency on an external service and per-request pricing.

Relationships

is invoked by dependency

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.