Agentic AI Reference Architecture

Safety & Security · Software component

Third-Party Moderation Service

Software componentSafety & SecuritySafety, Security & Governancearc:ThirdPartyModerationService

A moderation inference service consumed as an external API that scores submitted content for toxicity or other harm categories.

Responsibility. Scores content via an externally operated moderation API.

Also known as: API-based classifier, Content moderation API, Toxicity detector, Harmful content detection, Content Moderation Service

Variant of Moderation Inference Service abstract

When to choose. Choose when ease of integration outweighs dependency on an external service and per-request pricing.

is invoked byis invoked byspecializesis target of alternativeToOutput Rail: is invoked byOutput RailInput Rail: is invoked byInput RailModeration Inference Service: specializesModeration Inference Ser…Self-Hosted Moderation Service: is target of alternativeToSelf-Hosted Moderation S…
Direct neighbourhood (hover for relationship types)

Relationships

is invoked by dependency

alternative to variability

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Technologies
Perspective APIAzure Content ModeratorOpenAI Moderation APIGoogle Perspective APIActiveFence
Quality attributes
Compatibility (ISO/IEC 25010)Safety (ISO/IEC 25010 | NIST AI RMF: safe)Maintainability (ISO/IEC 25010)
Risks mitigated
Toxic contentHate speechViolenceSelf-harm content

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.
  2. Ch9.5: T. Nguyen, "Constitutional AI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.5. ISBN: 9798244538229.
  3. Ref9.01: "AI Safety Frameworks for Agent Systems," unpublished reference note (01-AI-Safety-Frameworks.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note
  4. Ref9.04: "Safety Guardrails Implementation for Agent Systems," unpublished reference note (04-Safety-Guardrails-Implementation.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note