> For the complete documentation index, see [llms.txt](https://docs.crobox.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.crobox.com/how-to-guides/sagent/how-to-use-analytics.md).

# How to Use Analytics

### Overview

Use **Analytics** to monitor Sagent performance and explore conversation data.

Analytics includes two subtabs:

* **Dashboard**
* **Ask Analytics**

Both subtabs use the same top-level filters:

* **Locale**
* **Date range**

Use these filters first. They shape the data shown in both views.

### What you can do in Analytics

Use Analytics to:

* track core usage and outcome metrics
* compare performance over time
* ask plain-language questions about conversation data
* add generated charts to the dashboard

### Dashboard tab

#### How to use the dashboard tab

{% stepper %}
{% step %}

#### Open the Dashboard subtab

Open **Analytics** and stay on **Dashboard**.
{% endstep %}

{% step %}

#### Choose your locale and date range

Use the **Locale** filter to focus on one market or language. Use the date picker to define the period you want to review.
{% endstep %}

{% step %}

#### Review the default metrics

The Dashboard tab shows a set of default metric cards. Use them as a quick health check.
{% endstep %}

{% step %}

#### Compare changes across cards

Do not read one metric in isolation. Check whether multiple cards move together.
{% endstep %}
{% endstepper %}

#### Default metrics

The Dashboard tab includes four default cards:

* **Sessions**
* **Completion Rate**
* **CTA Clicks**
* **Conversion Rate**

Each card uses a chart area and a short description.

Each card also includes a three-dot menu.

#### Sessions

This card shows the total number of user sessions. Use it to understand overall usage volume. Changes can reflect updates to prompts or product selection.

#### Completion Rate

This card shows the percentage of users who complete the experience. It focuses on users who reach recommendations. Drops may indicate usability issues.

#### CTA Clicks

This card shows how often users click CTA elements. Changes can follow prompt changes. Use it to understand action-taking behavior.

#### Conversion Rate

This card is part of the Dashboard layout. It is currently marked as **Coming soon**.

#### How to read the dashboard tab

Start with these checks:

1. Compare the current period with the previous one.
2. Look for shifts across more than one card.
3. Match the change to recent prompt or catalogue updates.

Some examples:

* **Sessions drop** and **CTA Clicks drop** — usage may be lower overall.
* **Sessions stay stable** and **Completion Rate drops** — review the flow for friction.
* **Completion Rate rises** and **CTA Clicks rise** — users may be moving through the experience more effectively.

### Ask Analytics tab

#### How to use the Ask Analytics tab

Use **Ask Analytics** to query your conversation data in plain language.

This tab turns a question into a chart and summary.

{% stepper %}
{% step %}

#### Open Ask Analytics

Open **Analytics** and click **Ask Analytics**.
{% endstep %}

{% step %}

#### Set the same filters first

Choose the **Locale** and **Date range** before asking a question. These filters define the scope of the result.
{% endstep %}

{% step %}

#### Start with a suggested prompt

The interface shows example prompts you can click. These help you start quickly.
{% endstep %}

{% step %}

#### Enter your own analytics request

Use the input field at the bottom of the page. Type your request in plain language.
{% endstep %}

{% step %}

#### Review the generated answer

The result includes a written summary and a chart. Use both together when you interpret the output.
{% endstep %}

{% step %}

#### Add useful results to the dashboard

Use **Add to Dashboard** when you want to keep the chart.
{% endstep %}
{% endstepper %}

#### Suggested prompts

Example prompts include:

* average sentiment score as a line graph
* number of messages and unique users per day
* most recommended product per week
* most mentioned topics in a table
* intents per day
* most active day of the week

These examples show the kinds of questions the tab supports.

#### Generated result view

The result area includes:

* a chat-style user request
* a written explanation of the result
* a chart card with title and subtitle
* an **Add to Dashboard** button

A result can include a line chart for average user sentiment over time.

#### Resetting the chat

Use **Reset Chat** to clear the current conversation. This helps when you want to start a new analysis path.

### Filters and shared controls

Both subtabs use the same shared controls at the top:

* **Locale**
* **Date range**

Use the same filter values when you compare Dashboard metrics with Ask Analytics results.

This keeps the analysis consistent.

### Best practices

Use Analytics regularly, not only after changes. Start with **Dashboard** for a quick overview. Then use **Ask Analytics** to investigate a specific question. When you find a useful view, add it to the dashboard.


---

# 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.crobox.com/how-to-guides/sagent/how-to-use-analytics.md?ask=<question>&goal=<endgoal>
```

`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.