> 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/sipgate-ai-agents/wie-kann-ich-ci-webhooks-fur-sipgate-conversational-intelligence-einrichten.md). # How can I set up CI webhooks for sipgate Conversation Intelligence? CI Webhooks are part of [Conversation Intelligence](/cloud-telefonanlage/en/using-sipgate/die-sipgate-app/was-ist-sipgate-conversation-intelligence.md). With CI Webhooks, call data from sipgate calls can be automatically sent to external systems such as a CRM. This allows call logs, summaries, and classifications to be directly integrated into existing processes. {% hint style="info" %} CI Webhooks are configured in the **web app** and must be distinguished from the separate AI Assist Webhook, which is set up directly in the sipgate Desktop App (see [How do I set up the sipgate AI Assist Webhook?](/cloud-telefonanlage/en/using-sipgate/die-sipgate-app/wie-richte-ich-den-sipgate-ai-assist-webhook-ein.md)). {% endhint %} #### Prerequisites * You have a target URL to which the data should be sent. * Your system is able to process HTTP POST requests with JSON payload and Tranfer-Encoding: chunked. * The webhooks only work for shared channels. Calls conducted over a private channel do not trigger CI webhooks. #### Typical use cases * CRM integration: Automatic transfer of call notes to customer records. * Support systems: Creation of tickets after incoming calls. * Analytics: Forwarding classifications to a reporting tool. #### Store webhook destinations 1. Log in as an admin in the **web app** at. 2. Open the Conversation Intelligence section in the settings. 3. Open the CI Webhooks configuration 4. Enter the desired webhook URL. #### How it works * After a call ends, sipgate sends the call data via HTTP POST to the stored webhook URL. * The data is transmitted as a JSON payload. * Your system can then store or further process this payload (e.g. in the CRM, ticket system, or internal databases). Example:\ A call ends ➔ call log is created ➔ data is automatically forwarded to your database ➔ your team has the information available immediately. Example payload: ``` { "version": "1", "call": { "id": "pbx-a1b2c3d4-e5f6-7890-abcd-ef1234567890", "from": "4921163553400", "to": "4921163553401", "startTime": "2026-04-08T09:22:41.663Z", "endTime": "2026-04-08T09:24:04.329Z", "duration": 82666, "direction": "IN", "users": [ { "userId": "w0", "accountId": "1234567", "fullUserId": "1234567w0", "firstName": "Max", "lastName": "Mustermann", "fullName": "Max Mustermann" } ], "channel": { "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479", "name": "Support Channel" } }, "assist": { "provider": { "llm": "AZURE" }, "transcription": { "content": "Caller: Good day, I'm calling about my contract. I received an invoice last week that was higher than expected.\nCallee: Good day, I'd be happy to take a look. Could you give me your customer number?\nCaller: Yes, it's 12345. Also, I'd like to know whether I can change my tariff.\nCallee: I can see the invoice. The amount is correct, as an additional package was booked. Of course, we can make a tariff change. I'll send you the options by email.", "chunks": [ { "speaker": "CALLER", "startTime": 3200, "endTime": 12400, "content": "Good day, I'm calling about my contract. I received an invoice last week that was higher than expected." }, { "speaker": "CALLEE", "startTime": 13100, "endTime": 18900, "content": "Good day, I'd be happy to take a look. Could you give me your customer number?" }, { "speaker": "CALLER", "startTime": 19500, "endTime": 26300, "content": "Yes, it's 12345. Also, I'd like to know whether I can change my tariff." }, { "speaker": "CALLEE", "startTime": 27000, "endTime": 40100, "content": "I can see the invoice. The amount is correct, as an additional package was booked. Of course, we can make a tariff change. I'll send you the options by email." } ] }, "callScenarios": null, "callHeadline": { "content": "Invoice inquiry and tariff change" }, "summary": { "content": "The customer called about an unexpectedly high invoice. The amount was correct, as an additional package was active. In addition, a tariff change was discussed; the options will be sent by email.", "keyPoints": [ "The invoice was correct — the increased amount resulted from a booked additional package.", "The customer would like to change their tariff.", "The available tariff options will be sent by email." ], "topics": [ "Invoice", "Additional package", "Tariff change" ] }, "actionItems": [ { "content": "Send tariff options to the customer by email." }, { "content": "Check the additional package and cancel it if necessary." } ], "smallTalkItems": [ { "topic": "Greeting", "description": "Both participants greeted each other at the beginning of the conversation." } ] } } ``` #### Security To ensure that only requests from sipgate are forwarded to your webhook integration, check the source IP address of incoming requests. To do so, add the following IP address to your allow list:\ 217.116.118.254 --- # 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://help.sipgate.de/cloud-telefonanlage/en/using-sipgate/sipgate-ai-agents/wie-kann-ich-ci-webhooks-fur-sipgate-conversational-intelligence-einrichten.md?ask=&goal= ``` `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.