Skip to content

Glossary: AI Security and Guardrails

Classifier (input, output)

Also written: classifier, classifiers, input classifier, output classifier

A model that sorts text into categories instead of writing a reply. Input classifiers check text before the main model reads it, and output classifiers check the reply before anyone sees it.

Where the book teaches it

Related terms

Catch rateFalse positive rateFail closedModeration model