> For the complete documentation index, see [llms.txt](https://docs.flashback.tech/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flashback.tech/flashgate-platform/organization/policies.md).

# Policies

The **Policies** section is where your organization defines AI governance and safety rules.

## Policy scopes

Policies can be defined at three levels:

* **Organization scope** (global defaults)
* **Workspace scope** (team or environment-specific)
* **Repository scope** (fine-grained, endpoint-level control)

## What policies are used for

Policies are AI guardrails for LLM traffic and AI usage. They can be used to:

* reduce privacy/compliance risk,
* detect or block sensitive data exposure,
* enforce usage constraints,
* standardize behavior across teams.

Examples include:

* PII handling constraints,
* redaction requirements,
* disallowed content classes,
* logging and alerting behavior.

## Policy building blocks

A robust policy usually includes:

* a **scope** (where it applies),
* a **risk level**,
* one or more **actions** (log, alert, block, etc.),
* a clear natural-language rule describing intended behavior.

## Relationship with Private Chat

Private Chat traffic that uses repository AI resources is subject to policy evaluation. This gives admins visibility and control over how AI interactions are handled across the organization.

## API mapping

See: [AI Policy API](/support-reference/platform-api-reference/ai-apis/ai-policy.md)


---

# 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:

```
GET https://docs.flashback.tech/flashgate-platform/organization/policies.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.