> 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/analytics.md).

# Analytics

**Analytics** gives you a complete view of usage, people, models, Experts, and tools across the workspace.

Here are the available features:

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

To adjust the data shown, use the filters at the top of the page:

* **Period:** sets the date range. The default is **Last 30 days**.
* **Teams:** filters the data by team. The default is **All teams**.
* **Refresh:** reloads the data with the latest information.

Below the title, you'll see the selected date range, the number of active users, and the total credits used.

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

To export usage data, follow these steps:

1. At the top of the page, click **Export CSV**.
2. Select the export option you want.

> You can import the CSV file into your company's BI tool.

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

Analytics is organized into the following tabs: **Overview**, **Users**, **Teams**, **Models**, **Experts**, and **Tools**.

### Overview <a href="#overview" id="overview"></a>

#### Metrics <a href="#metrics" id="metrics"></a>

Each card shows the period total, a trend chart, and the percentage change:

* **Messages:** total messages exchanged.
* **Active users:** active users out of the total.
* **Conversations:** total conversations started.
* **Tokens:** total token volume, split into input and output.
* **Credits used:** total credits consumed.
* **New users:** users who started using Astro during the period.

#### Usage charts <a href="#usage-charts" id="usage-charts"></a>

* **Daily usage:** usage over the period. Click **Messages** or **Tokens** to switch the metric shown.
* **Activity by hour:** messages by hour of the day, in your browser's time zone.

#### Rankings <a href="#rankings" id="rankings"></a>

* **Top users:** each user's share of messages during the period.
* **Top models:** each model's and Expert's share of requests during the period.

#### Alerts <a href="#alerts" id="alerts"></a>

The **Alerts** panel highlights signals that need the administrator's attention:

* **Inactive users** (Info): users with no activity for more than 30 days.
* **Unusual usage** (Warning): users whose usage is more than 3× the average.

Each alert shows the number and names of the users involved.

#### Tool usage <a href="#tool-usage" id="tool-usage"></a>

At the bottom of the page, cards show how many times each tool was used during the period:

* **Web searches**
* **File searches**
* **Code executions**
* **Images generated**
* **Videos generated**
* **Conversations with Experts**
* **Files uploaded**, with total volume in MB


---

# 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/analytics.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.
