Pattern
Meta Llama Guard
Provide a fast, classification-focused safety model that classifies inputs and outputs as safe or unsafe across a defined taxonomy of harm categories, deployable in front of a main agent LLM at sub-100ms latency.
Classification — Specialized safety-classification model deployable as a guardrail.
Full entry
The complete treatment — problem, how it works, when to use it, sources, and examples — lives in the volume below.
Browse the full pattern index or the catalog.