# Guard models

Guard models are classifiers trained to judge whether a prompt, a response or a tool call breaks a policy. They run on every request beside the main model, so they are kept small and fast.

## How they work

A guard model takes one message or tool call and returns a verdict: whether it breaks a [policy](/glossary/guardrail-policy), and which one. Some learn a fixed set of categories in training. Others read the policy text along with the content, so a rule can be added without retraining.

## Why they are small

The check sits in the path of every request, so its [latency](/glossary/guardrail-latency) is added to every answer. Classifying is a narrow job, so a guard model can be far smaller and faster than the model it guards.

## How they are kept accurate

- **Labeled data.** They are trained on traffic that breaks each policy and traffic that does not. See [classification fine-tuning](/glossary/classification-fine-tuning).
- **A larger model.** It re-checks the small model's verdicts off the request path, where its slowness delays nobody, and its verdicts become training data. This is a form of [knowledge distillation](/glossary/knowledge-distillation).
- **New attacks.** The model is retrained on what red teaming and live traffic turn up.

## With White Circle

We train our own guard models: a small one gives verdicts in real time, a larger one confirms them, and the larger model's verdicts are then used to improve the small one. [Control](/products/control) analyzes every input and output in real time.

