Agentic AI Reference Architecture

Safety & Security · Software component

Disclaimer Injector

Software componentSafety & SecuritySafety, Security & Governancearc:DisclaimerInjector

An output guardrail that modifies responses to meet standards by appending domain-appropriate compliance disclaimers or converting absolute statements into hedged language.

Responsibility. Adds required disclosures to outgoing responses.

Also known as: Modify guardrail, add disclaimers flow

guardsis orchestrated byis configured byLLM Inference Service: guardsLLM Inference ServiceGuardrail Orchestrator: is orchestrated byGuardrail OrchestratorCompliance Policy Rule Set: is configured byCompliance Policy Rule Set
Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

guards control

is orchestrated by control

Design guidance

Classification

Technologies
NeMo GuardrailsColang
Risks mitigated
Missing legally required disclosuresResponses construed as medical, legal or financial advice

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. Ref9.04: "Safety Guardrails Implementation for Agent Systems," unpublished reference note (04-Safety-Guardrails-Implementation.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note