> For the complete documentation index, see [llms.txt](https://help.sipgate.de/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.sipgate.de/conversation-intelligence/conversation-intelligence-en/use-analytics.md).

# Use analytics

In the Analytics view, you can see at a glance how the results of your Custom Fields develop over time, without having to search individual conversations in the Data Hub. This way, you can recognize pat

{% hint style="info" %}
**Note:** Analytics is in beta. Features and appearance may still change.
{% endhint %}

#### What does the Analytics view show?

For each custom field with the response type **Yes/No** a separate section with three charts appears:

* **Distribution:** A donut chart shows how the conversations in the selected period are distributed across the values (e.g. yes and no). Above it, you can see the total number of analyzed conversations.
* **Trend:** A bar chart shows the **number** of conversations per value over time.
* **Trend:** A line chart shows the **percentage share** per value over time. This lets you recognize developments even when the total number of conversations changes.

Conversations in which the custom field is not filled in are not taken into account in the value distribution.

#### How do I select the time period?

Using the time period selector above the charts, you can choose today, yesterday, the last 7 or 30 days, or a custom period. All charts on the page adjust accordingly. The time axis is selected automatically: for short periods you see hours, for longer ones days or weeks.

#### How do I get from a chart to the conversations?

The charts are clickable. Clicking opens the Data Hub with the appropriate filter and time period so you can see the underlying conversations:

* **Distribution:** Clicking a value shows all conversations with this value in the selected time period.
* **Trend:** Clicking a bar shows the conversations with this value in the respective time segment.
* **Trend:** Clicking a time point shows all conversations with a filled value in the respective time segment.

#### When do I see charts?

The Analytics view shows analyses as soon as you have created at least one suitable custom field. Otherwise, you will see a notice with a link to manage custom fields. If you create a custom field there, charts will be shown after the first analyzed conversations.

#### Good to know

* The analysis is based on the results of your custom fields. The more clearly a field is defined, the more meaningful the charts are.
* Analytics is used to observe patterns in your business, not to evaluate individual employees (see [privacy](broken://pages/3d091869b0db4e87a536e742783aeabed22fb243)).
* If you want to be automatically informed about noticeable changes, set up a [notification](broken://pages/02b5cf1d1e3cea669ffdfdeea5cc0622bb969c5b) .


---

# 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://help.sipgate.de/conversation-intelligence/conversation-intelligence-en/use-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.