> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://nemo-platform.docs.buildwithfern.com/nemo/platform/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://nemo-platform.docs.buildwithfern.com/nemo/platform/_mcp/server.

# Guardrail Configurations

<a id="guardrails-configurations" />

Guardrail configurations define the safety policies that protect your LLM interactions. A configuration specifies which safety checks (rails) to apply, the models to use, and the prompts to use for the safety checks.

***

## Overview

A guardrail configuration contains several properties that customize how the service interacts with models and applies safety checks. Most configurations define these core components:

1. **Models** – The models to use for each task.
2. **Prompts** – Prompt templates to use for each task.
3. **Rails** – Configuration that defines how to apply checks on the user input or LLM output.

A guardrail configuration also supports general options such as instructions and sample conversations that you can customize.

***

## In This Section

Learn about models, prompts, and rails that make up a configuration.

Create, list, retrieve, update, and delete guardrail configurations.

Built-in configurations available in the `system` workspace: `default`, `content-safety`, and `self-check`.