> For the complete documentation index, see [llms.txt](https://docs.oveka.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.oveka.io/core-concepts/promptguard.md).

# Promptguard

Learn how PromptGuard monitors and controls the use of AI across your organization.

## Overview

PromptGuard is Oveka’s AI monitoring and protection component. It provides visibility into how AI is being used across your organization and allows you to control which AI platforms can be accessed and what data can be shared with them.

With PromptGuard you can:

* **Control AI platform access** – choose which AI platforms users are permitted to access.
* **Monitor AI usage** – understand which AI platforms are being used across your organization.
* **Protect sensitive data** – detect sensitive information being shared with AI platforms and block or redact it according to your policies.
* **Control file uploads** – monitor and restrict files being uploaded to AI platforms.
* **Restrict unapproved AI** – prevent users from accessing AI platforms that have not been approved by your organization.

PromptGuard is designed to provide these controls without preventing users from taking advantage of approved AI tools.

## How it works

PromptGuard uses an agent deployed to end-user devices. Once installed, the agent connects to Oveka and monitors AI activity in real time.

When a user interacts with a supported AI platform, PromptGuard evaluates the activity against the policies configured for their organization.

Depending on those policies, PromptGuard can:

* Allow the interaction normally.
* Detect and classify data being shared with AI.
* Redact sensitive information before it is shared.
* Block prompts or file uploads containing restricted data.
* Block access to unapproved AI platforms.
* Record activity for visibility and reporting.

This allows organizations to apply consistent AI protection policies across users without requiring individual AI platforms to be configured separately.

## Supported platforms

PromptGuard is under active development, with support being expanded across browsers, operating systems, and network environments.

#### Currently supported and planned deployment methods

<table><thead><tr><th>Platform</th><th width="228.4921875">Installation Method;</th><th>Status</th><th>Supported OS</th></tr></thead><tbody><tr><td>Chrome Browser</td><td>Chrome Extension</td><td>Available Now</td><td>Windows/OSX/ChromeOS</td></tr><tr><td>Edge Browser</td><td>Chrome Extension</td><td>Available Now</td><td>Windows/OSX</td></tr><tr><td>Windows</td><td>Local Agent</td><td>Under Development</td><td>Windows 11</td></tr><tr><td>OSX Agent</td><td>Local Agent</td><td>Under Development</td><td>OSX</td></tr><tr><td>Network Proxy</td><td>Docker</td><td>Under Consideration</td><td>NA</td></tr></tbody></table>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.oveka.io/core-concepts/promptguard.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.