> For the complete documentation index, see [llms.txt](https://docs.agentalk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agentalk.io/integrations/use-webhooks-for-post-call-automation.md).

# Use webhooks for post-call automation

Webhooks send call data from Agentalk to an external system in real time. This is useful for automating workflows such as updating a CRM, triggering follow-ups, or storing call results.

After each call ends, Agentalk sends a request to your webhook URL with the conversation summary and key call data.

### Before you start

You need the following before you begin:

* A webhook endpoint (URL) that can receive HTTP requests.
* A system to process the data (such as a CRM, database, or automation tool like Make or n8n).

### Configure a webhook

Set up a webhook to receive call data after each call.

Follow these steps to configure a webhook and start receiving call data.

1. Go to **AI Agents** from the sidebar.
2. Select the agent you want to configure.
3. Scroll to **Additional settings** and click to expand the section.
4. Locate **Conversation Summary Webhook (Optional)** and enter your webhook URL.
5. Click **Save.**

<figure><img src="/files/7HmtFFnRAC9SxdiUzewm" alt=""><figcaption></figcaption></figure>

After saving, the webhook is triggered automatically after every call handled by this agent.

### What data is sent

When a call ends, Agentalk sends a request to your webhook URL.

This may include:

* Contact information
* Conversation summary
* Call duration
* Call outcome or status
* Recording reference (if available)

Use this data to power automations or store call results in external systems.

### Preview the webhook payload

The payload preview shows the JSON your endpoint will receive before you run a real call. Use it to build and test your parser before live traffic starts.

1. Open the agent editor.
2. Scroll to the **Webhooks** section.
3. Click **Webhook Payload Preview**.
4. Review the expanded JSON sample.
5. Click **Copy to Clipboard** to copy the payload.
6. Paste it into your handler, test tool, or local workflow.

The expanded panel shows:

* A short description of the sample
* A syntax-highlighted JSON body
* A **Copy to Clipboard** button

Click the row again to collapse the preview.

### When to use webhooks

Webhooks are useful when you want to automate actions after each call.

Common use cases include:

* Updating a CRM with call results.
* Sending follow-up messages or notifications.
* Logging call data in a database or spreadsheet.
* Triggering workflows in tools like Make or n8n.

### Test your webhook

Before using this in production, verify that your webhook is working correctly.

* Use a test URL (such as a webhook testing tool).
* Run a test call.
* Confirm that your endpoint receives the data.

This helps ensure your automation runs reliably.

### Inspect recent deliveries

Recent deliveries show the latest webhook calls sent for this agent. Use this panel to confirm delivery, inspect failures, and understand retry behavior.

1. Open the agent editor.
2. Scroll below the payload preview.
3. Open **Recent Webhook Deliveries**.
4. Review the table for the latest attempts.
5. Check the status, HTTP code, latency, and retry count.
6. If loading fails, click **Retry**.

The panel shows deliveries from the last 7 days, up to the 10 most recent attempts.

Each row includes:

| Column           | What it shows                               |
| ---------------- | ------------------------------------------- |
| **Sent**         | When the system attempted delivery          |
| **Event Type**   | Which event triggered the webhook           |
| **Target URL**   | Where the request was sent                  |
| **HTTP Status**  | The response code returned by your endpoint |
| **Latency (ms)** | How long the endpoint took to respond       |
| **Attempts**     | Total delivery attempts, including retries  |
| **Status**       | Pending, Delivered, Failed, or Exhausted    |

If you see repeated **Failed** or **Exhausted** rows, check the response code and latency first. Long response times can cause timeouts that count as failures.

If the agent has no deliveries yet, the panel shows **No recent webhook deliveries to display.**

### Next steps

Here are the recommended next steps after completing this guide:

* [**API documentation**](/integrations/api-documentation.md): Learn how to securely connect Agentalk with external systems.
* [**Create an outbound campaign**](/campaigns/create-an-outbound-campaign.md): Start generating calls that can trigger your webhook.
* [**Manage contacts**](/contacts/manage-contacts.md): Prepare and organize contact data for automation workflows.


---

# 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.agentalk.io/integrations/use-webhooks-for-post-call-automation.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.