Agentic AI Reference Architecture

Safety & Security · Software component

Allow-List Output Filter

Software componentSafety & SecuritySafety, Security & Governancearc:AllowListOutputFilter

A content safety filter that permits only outputs explicitly enumerated in an approved set and blocks everything else.

Responsibility. Blocks any output not explicitly permitted.

Also known as: Allow list, Whitelist filter

Variant of Content Safety Filter abstract

When to choose. Choose for highly constrained applications with well-defined, limited acceptable outputs (template-based bots, approved code sets, near-zero risk tolerance); avoid for general-purpose applications needing natural, flexible responses.

specializesalternative toalternative tois configured byContent Safety Filter: specializesContent Safety FilterToxicity Classifier: alternative toToxicity ClassifierDeny-List Content Filter: alternative toDeny-List Content FilterOutput Allow List: is configured byOutput Allow List
Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

alternative to variability

Design guidance

Classification

Patterns
Default denyAllow listing
Quality attributes
Safety (ISO/IEC 25010 | NIST AI RMF: safe)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated
Adversarially induced outputs in constrained domains

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.