> 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/cloud-telefonanlage/en/using-sipgate/die-sipgate-app/wie-richte-ich-den-sipgate-ai-assist-webhook-ein.md).

# How do I set up the sipgate AI Assist webhook?

Set up the AI Assist webhook in the sipgate desktop app to automatically send AI Assist results from a channel to external systems.

With the AI Assist Webhook, you can automatically send the AI Assist results of a channel—such as transcript, summary, to-dos, and smart answers—to an external destination URL, for example to transfer them to a CRM or other tools with Zapier.

{% hint style="info" %}
The AI Assist Webhook is to be distinguished from the [CI Webhooks](/cloud-telefonanlage/en/using-sipgate/die-sipgate-app/wie-kann-ich-ci-webhooks-fur-sipgate-conversational-intelligence-einrichten.md) ; the AI Assist Webhook is set up in the **Desktop App** and transmits the AI Assist results of a single channel. CI Webhooks, on the other hand, are configured in the **Web App** and deliver Conversation Intelligence data across the entire account.
{% endhint %}

#### Prerequisites

* The webhook can only be set up by administrators of the sipgate account.
* It applies only to channels—so a channel with a phone number is required.

#### Where do I set up the webhook?

1. As an admin, open the sipgate Desktop App.
2. In the settings, open the section **AI Assist ➔ AI Assist Webhook**.
3. Enter the desired destination URL under **configure** and save the setting.
4. Select the desired data format: Standard JSON.
5. Save the setting.

After each call via a channel, the AI Assist results are automatically transferred as a bundle to the stored URL as soon as all content is available.

#### Payload format

**Standard JSON** includes, among others, the following fields:

```json
{
  "callHeadline": "...",
  "call": {
    "id": "...",
    "caller": "...",
    "callee": "...",
    "startTime": 0,
    "endTime": 0,
    "duration": 0,
    "direction": "inbound"
  },
  "channel": {
    "id": "...",
    "name": "..."
  },
  "transcriptions": [
    { "speaker": "caller", "startTime": 0, "endTime": 0, "text": "..." }
  ],
  "summary": "...",
  "actionItems": [{ "id": "...", "text": "..." }],
  "smallTalkItems": [{ "id": "...", "topic": "...", "description": "..." }],
  "smartAnswers": [{ "id": "...", "question": "...", "answer": "..." }]
}
```

You can find a practical application of the AI Assist Webhook with Zapier, HubSpot, Slack, and Google Sheets in the article [How do I use sipgate AI Assist in conjunction with HubSpot, Slack & Google Sheet?](/cloud-telefonanlage/en/connections-and-integrations/integrationen-fur-die-sipgate-app/wie-nutze-ich-den-sipgate-ai-assist-in-verbindung-mit-hubspot-slack-google-sheet.md)


---

# 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/cloud-telefonanlage/en/using-sipgate/die-sipgate-app/wie-richte-ich-den-sipgate-ai-assist-webhook-ein.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.