> 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/ai-protection.md). # AI Protection Learn how your organization is using AI and put sensible controls around what gets shared. #### Introduction People are already using tools like ChatGPT, Claude, and Copilot throughout their working day. The challenge is knowing which tools are being used and making sure sensitive information does not leave the organization along the way. AI Protection gives you that visibility and lets you put sensible controls around what employees can share. #### PromptGuard PromptGuard runs on managed devices, checks prompts for sensitive information, and applies your protections before the content reaches the LLM. Browser extensions provide coverage for Google Chrome and Microsoft Edge and can be deployed centrally through your preferred MDM. Native agents are also available for macOS and Windows. These extend coverage beyond the browser to native applications, command-line tools, and local coding agents. #### Configure protections Protections let you decide which platforms employees can use and what they are allowed to share. You can keep these rules broad across the organization or tailor them to particular groups. Depending on your requirements, you can: * Allow or block individual platforms. * Prevent credentials, passwords, API keys, and access tokens from being shared. * Restrict files and attachments. * Protect financial, health, identity, or other sensitive information. * Create custom policies for information specific to your organization. #### Reviewing activity The **Conversations** view gives you a clearer picture of how these tools are being used across the organization. You can see which platforms people are using, the general purpose and sensitivity of their conversations, and whether individual requests were allowed or blocked. Oveka also identifies relevant data classifications and uploaded files. Opening a conversation provides more context, including its messages, classifications, and any policy decisions that were applied. #### Configuring data retention Prompt and response retention can be configured for different groups of users. If retention is disabled, Oveka can continue protecting the user without storing the underlying prompts or responses. This gives organizations the flexibility to maintain safeguards while meeting their own privacy requirements. --- # 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://docs.oveka.io/core-concepts/ai-protection.md?ask=&goal= ``` `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.