# Probabilistic guardrail

A guardrail that uses a model or classifier, so its judgment can be wrong: it can miss bad content, block good content, or be tricked.

Also called: Model-based check, Classifier

Kind of: Guardrail

Related: LLM-as-judge, Probabilistic

Source: https://redfinchadvisory.com/lexicon/probabilistic-guardrail (version 1.0, changed 2026-10-21)