---
title: permissiveContentTransformations
framework: foundationmodels
role: symbol
role_heading: Type Property
path: foundationmodels/systemlanguagemodel/guardrails/permissivecontenttransformations
---

# permissiveContentTransformations

Guardrails that allow for permissively transforming text input, including potentially unsafe content, to text responses.

## Declaration

```swift
static let permissiveContentTransformations: SystemLanguageModel.Guardrails
```

## Mentioned in

Improving the safety of generative model output

## Discussion

Discussion The permissiveContentTransform guardrail model lets the model handle potentially unsafe content, such as summarizing a news article. In this mode, requests you make to the model that generate a String will not throw LanguageModelError.guardrailViolation(_:) errors. However, the model may still sometimes refuse to respond to a sensitive prompt, in which case it generates a String refusal message. When you generate responses other than String, this mode behaves the same way as default mode and throws LanguageModelError.guardrailViolation(_:) errors.

## See Also

### Getting the guardrail types

- [default](foundationmodels/systemlanguagemodel/guardrails/default.md)