> For the complete documentation index, see [llms.txt](https://docs.skyone.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.skyone.cloud/english/admin/audit.md).

# Audit

**Audit** shows a complete log of what each user does in Astro: prompts sent, responses, models, tools, files, and costs.

{% hint style="info" %}
Access to Audit is restricted to administrators.
{% endhint %}

Here are the available features:

### Browse the tabs <a href="#browse-the-tabs" id="browse-the-tabs"></a>

Records are organized into the following tabs:

* **Messages:** each prompt sent and each response generated, individually.
* **Conversations:** records grouped by conversation.
* **Saved prompts:** prompts saved by users in the Library.

### Filter records <a href="#filter-records" id="filter-records"></a>

To find specific records, follow these steps:

1. In the **Search content...** field, enter a keyword from the prompt or response.
2. Click the period selector to set the date range. The default is **Last 30 days**.
3. In **All users**, select a specific user if needed.
4. In **All models**, select a specific model or Expert if needed.
5. Choose the record type: **All**, **Prompts** (user messages only), or **Responses** (Astro responses only).

{% hint style="info" %}
Click the refresh icon next to **Export CSV** to reload the records.
{% endhint %}

### View a message <a href="#view-a-message" id="view-a-message"></a>

In the **Messages** tab, each row shows the following information:

* **Date/time:** when the message was sent or generated.
* **User:** name and email of the person in the conversation.
* **Source:** whether the message was sent by the **User** or generated by the **Assistant**.
* **Conversation:** title of the conversation where the message was exchanged.
* **Model:** model or Expert that generated the response.
* **Content:** the beginning of the message text. Click **See all** to read the full content.
* **Tokens:** number of tokens used by the message.

### Export records <a href="#export-records" id="export-records"></a>

To export records, follow these steps:

1. Apply the filters you want.
2. Click **Export CSV**.

{% hint style="info" %}
Use the CSV file to analyze the records in your company's BI tool.
{% endhint %}


---

# 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.skyone.cloud/english/admin/audit.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.
