# Guardrails

::::card-grid
:::card{title="Guardrails overview" href="/guides/guardrails-overview"}
Protect your LLM application in real time by blocking unsafe inputs and outputs
:::

:::card{title="Policies" href="/guides/guardrails-policies"}
Define your checks once in Opik and reference them by name from your application
:::

:::card{title="Guards" href="/guides/guardrails-guardrails"}
:::

:::card{title="Prompt injection model" href="/guides/guardrails-prompt-injection-model"}
Opik Guard, our purpose-built detection model, evaluated on attacks it has never seen
:::

:::card{title="Custom models" href="/guides/guardrails-custom-guardrails"}
Fine-tune a language model for a check the built-in guards do not cover
:::

:::card{title="Guardrails server" href="/guides/guardrails-server"}
Install, configure, and run the backend that powers the model-based guards
:::
::::

## Related pages

- [.NET](./net-index.md)
- [Administration](./administration-index.md)
- [AI Coding Assistants](./ai-coding-assistants-index.md)
- [Changelog](../changelog.md)
- [Configuration](./configuration-index.md)
- [Contributing](./contributing-index.md)
- [Development](./development-index.md)
- [Evaluation](./evaluation-index.md)
- [Getting Started](./getting-started-index.md)
- [Installation](./installation-index.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.