> 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/promptguard/insights-and-reporting/review-conversations-users-are-having-with-ai.md).

# Review conversations users are having with AI

Understand how AI is being used, what information is involved and whether activity needs further attention.

### Overview

Oveka PromptGuard provides visibility into the conversations users are having with AI platforms. This helps admins understand how AI is being used, what information is involved and whether activity needs further attention.

### Finding relevant conversations

The PromptGuard Conversations view provides a list of AI conversations across your organisation. Each entry shows the user, AI platform used, latest message time, a preview of the conversation text and classification tags.

Searching helps you find conversations relevant to what you want to investigate. You can narrow the results by searching for specific data or intention tags.

<figure><img src="https://1078805375-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FftH1qxxd9PrA9tzGguLX%2Fuploads%2FIBcvp1HkxleU0ne2r3tg%2FScreenshot%202026-10-07%20at%201.38.47%E2%80%AFPM.png?alt=media&amp;token=9d4ad991-8b4c-4a50-b0db-76657ed3c031" alt=""><figcaption></figcaption></figure>

### Understanding the conversation

Open an individual conversation to see the messages and understand what the user was trying to achieve.

Data classifications identify the types of information involved in the conversation, while intention classifications describe the task the user is looking to perform. Each message also shows a verdict, so you can see whether the request was allowed, blocked or user-approved.

Together, these insights help you understand the conversation and decide whether it needs further attention.

<figure><img src="https://1078805375-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FftH1qxxd9PrA9tzGguLX%2Fuploads%2FRxXXAojTflJjUqKsR9fz%2FScreenshot%202026-10-07%20at%201.13.10%E2%80%AFPM.png?alt=media&amp;token=d63babf3-e8e1-43a1-9a31-668934744f3e" alt=""><figcaption></figcaption></figure>

### Acting on what you find

Reviewing conversations can help you:

* Understand how users are applying AI to their work.
* Follow up on unexpected or concerning activity.
* Give users guidance based on real examples.
* Identify where protection policies may need adjusting.

#### FAQs

<details>

<summary><strong>Does a recorded conversation mean every request was allowed?</strong></summary>

No. Each message has its own verdict, which you can see within the conversation.

</details>

<details>

<summary><strong>Can I find conversations involving a particular type of information?</strong></summary>

Yes. Use the search in Conversations to narrow the results by classification tags.

</details>

<details>

<summary><strong>Does a classification tag mean the activity needs investigation?</strong></summary>

Not necessarily. Consider the conversation context, your organisation’s policies and the message verdict before deciding whether action is needed.

</details>

<details>

<summary><strong>Can I disable storage of prompt and response content?</strong></summary>

Yes. You can [disable prompt and response retention](https://docs.oveka.io/promptguard/privacy-and-prompt-history.md). Conversations will still be classified with data and intention tags, without storing the conversation content.

</details>


---

# 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/promptguard/insights-and-reporting/review-conversations-users-are-having-with-ai.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.
