> 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/data-hub.md).

# Data Hub

All call data is collected in the Data Hub. Here you can view, filter and export your results.

#### Where can I see my call data?

All calls are captured, enriched and stored in structured form in the Data Hub. This includes the call metadata as well as the [Custom Fields](broken://pages/f5356f5e4741b153b3ec3ac8a330295c3b2cc309) including the transcript.

#### How do I filter results?

The Data Hub has extensive filtering functionality that lets you narrow down your call data in a targeted way. You can combine multiple filters using **AND** and **OR** to restrict the overall result based on various column values, for example to show only calls from a certain team, on a certain topic, or with a missing summary.

Each filter consists of three building blocks:

1. **Column:** Which column should the filter refer to?
2. **Operator:** How should the comparison be made?
3. **Value:** What should it be compared with?

For example: column “Topic”, operator “contains”, value “invoice” shows you all entries whose topic contains the word “invoice”.

#### Which operators are available?

| Operator             | Meaning                                                    | Example                                                                                  |
| -------------------- | ---------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| **contains**         | The column value contains the entered text anywhere.       | “Topic contains *invoice*" finds “invoice inquiry” and “wrong invoice”.                  |
| **does not contain** | The column value does not contain the entered text.        | “Topic does not contain *spam*" hides all spam entries.                                  |
| **is equal to**      | The column value exactly matches the entered value.        | “Team is equal to *Support*" shows only entries with exactly the value “Support”.        |
| **is not equal to**  | The column value does not exactly match the entered value. | “Direction is not equal to *outgoing*" hides outgoing calls.                             |
| **starts with**      | The column value starts with the entered text.             | “Phone number starts with *+4930*" shows Berlin phone numbers.                           |
| **ends with**        | The column value ends with the entered text.               | “Email ends with *@example.com*" shows contacts from a specific domain.                  |
| **is empty**         | The column contains no value.                              | “Summary is empty” shows calls without a summary. No value is needed for this operator.  |
| **is not empty**     | The column contains a value.                               | “Note is not empty” shows only entries that have a note. Again, no value is needed here. |

#### How do I filter on multiple values at the same time?

If you want to check multiple values at the same time within a column, you do not need to create multiple individual filters. There are four operators for this, where you can specify a list of values:

| Operator                        | Meaning                                                              | Example                                                                                                                 |
| ------------------------------- | -------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| **contains one of the values**  | The column value contains at least one of the specified values.      | “Topic contains *cancellation, contract, tariff*" finds all conversations in which at least one of these words appears. |
| **contains none of the values** | The column value contains none of the specified values.              | “Topic contains none of the values *spam, test*" hides both categories.                                                 |
| **is one of the values**        | The column value exactly matches one of the specified values.        | “Team is one of the values *Support, Sales*" shows entries from both teams.                                             |
| **is none of the values**       | The column value does not exactly match any of the specified values. | “Status is none of the values *missed, canceled*" shows only successfully completed calls.                              |

#### How do I combine filters with AND and OR?

You can create as many filters as you like and combine them via the links **AND** and **OR** combine. Within a filter list, you cannot mix AND and OR. Once you have chosen a link, it applies to all further conditions.

* **AND:** All conditions must be met simultaneously. The result becomes narrower with each condition.
* **OR:** At least one of the conditions must be met. The result becomes broader with each condition.

**Example 1 (AND):** “Team is equal to *Support*" AND “Topic contains *invoice*" shows only calls from the Support team in which the topic was invoices.

**Example 2 (OR):** “Topic contains *cancellation*" OR “Topic contains *complaint*" shows all calls in which the topic was cancellations or complaints.

{% hint style="info" %}
If you want to combine AND and OR logic (e.g. “Team is *Support* AND the topic is *cancellation* OR *complaint*"), use the operators for multiple values: “Team is equal to *Support*" AND “Topic contains one of the values *cancellation, complaint*". This lets you map the OR logic within a single condition and combine the entire list with AND.
{% endhint %}

<figure><img src="https://702748557-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FcPbcWJCrFgi79rVOgXbo%2Fuploads%2FIqaU0QybcgO12FUAjuYP%2F07-data-hub-filter.png?alt=media&amp;token=7bde4640-fb41-4b7c-9b4b-1e055e344ea5" alt=""><figcaption></figcaption></figure>

#### What typical filters are there?

* **Find calls without a result:** “Summary is empty” shows which conversations have not yet been evaluated.
* **Keep track of specific topics:** “Topic contains *cancellation, price increase, change*" is suitable for monitoring churn signals.
* **Hide a channel:** “Channel is not equal to *internal*" focuses the view on customer conversations.
* **Calls from a company:** “Organization contains *Example Ltd.*" shows all calls that were assigned to the company. A requirement is a [contact integration](broken://pages/8fcbd59a3e774981a89b30bd1992121ab6183315).
* **Regional analysis:** “Phone number starts with *+4989*" shows calls from the Munich area.

{% hint style="info" %}
Filters always affect only the view. Your data remains unchanged. The operators **is empty** and **is not empty** do not require a comparison value.
{% endhint %}

#### How do I export data?

You can export the data in the Data Hub at any time, for example to further process it in Excel or archive it as a report. During export, only the filtered data set is taken into account, not the complete unfiltered data set.

{% stepper %}
{% step %}

## Filter results

If necessary, narrow down the results using the filters.
{% endstep %}

{% step %}

## Export data

Click **Export data**.
{% endstep %}

{% step %}

## Download CSV file

The data is downloaded as a **.csv file** .
{% endstep %}
{% endstepper %}

The exported .csv file can be imported into common spreadsheet programs such as Microsoft Excel. You can find instructions for this at Microsoft: [Import CSV file into Excel](https://support.microsoft.com/de-de/excel/import-data-from-a-csv-html-or-text-file).

Data that you do not want to export, but want to process automatically, can be retrieved via [Webhook](broken://pages/b6f046ffa25e8a56417363b67238fcfcc217d673) or via the [MCP server](broken://pages/d108124e252725666a24341fde84708c7080cfec) .


---

# 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/data-hub.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.