> For the complete documentation index, see [llms.txt](https://karini-ai.gitbook.io/karini-ai-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://karini-ai.gitbook.io/karini-ai-documentation/guardrails/guardrail-usage.md).

# Guardrail usage

Once Guardrails are created, they can be integrated across key components of the platform to ensure responsible and controlled AI behavior. The following outlines how guardrails are applied at each stage:

* [**Prompt Playground**](/karini-ai-documentation/guardrails/guardrail-usage/prompt-playground.md):\
  Guardrails can be applied to prompts during the design and testing phase. This allows users to evaluate how the guardrails influence output, enforce constraints, and mitigate undesirable responses before deploying prompts to production workflows.
* [**Recipe**](/karini-ai-documentation/guardrails/guardrail-usage/recipes.md):\
  Guardrails configured in the Prompt Playground can be linked to prompts within a Recipe. In this context, guardrails act as enforcement layers that ensure prompts behave consistently and adhere to organizational policies, such as restricting certain topics or enforcing output formatting rules.
* [**Copilot**](/karini-ai-documentation/guardrails/guardrail-usage/copilot.md):\
  When Recipes are embedded into Copilots, the associated guardrails continue to function in real time. This ensures that end-user interactions are moderated by the same safety, compliance, or domain-specific constraints defined earlier, maintaining integrity and trustworthiness in production environments.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://karini-ai.gitbook.io/karini-ai-documentation/guardrails/guardrail-usage.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.