> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/integrations/block-integrations/search_monitor_trigger.md).

# Exa Search Monitor Trigger

Blocks for starting a workflow when an Exa Search Monitor posts an event to its webhook.

## Exa Search Monitor Trigger

### What it is

Triggers when an Exa Search Monitor reports new results. Paste this block's webhook URL into Exa Create Search Monitor, then paste the monitor's webhook secret here.

### How it works

This block gives you a webhook URL to paste into Exa Create Search Monitor; nothing is registered with Exa automatically. When `webhook_secret` is set, each delivery's `Exa-Signature` header (HMAC-SHA256 of the timestamp and body) is checked and unsigned or mismatched deliveries are rejected, as is a delivery whose signed timestamp is more than five minutes from the current time. Until it is set, any request to the URL is accepted. By default only `monitor.run.completed` starts the workflow; it carries the run's results, or why it failed, so check `status` and `fail_reason` before using the results.

For run events the block outputs the run's ID, status, new results (as a list and one at a time), synthesized content, grounding and fail reason. For monitor created, updated and deleted events it outputs the monitor instead. The monitor's metadata is output for every event.

### Inputs

| Input           | Description                                                                                                                                                                                                                                          | Type   | Required |
| --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------ | -------- |
| webhook\_secret | The webhook\_secret output of Exa Create Search Monitor (Exa shows it only once). When set, deliveries without a valid Exa signature are rejected. Strongly recommended: until it is set, anyone who knows this block's URL can send it fake events. | str    | No       |
| events          | Which monitor events start the workflow                                                                                                                                                                                                              | Events | No       |

### Outputs

| Output       | Description                                                                              | Type                    |
| ------------ | ---------------------------------------------------------------------------------------- | ----------------------- |
| error        | Error message if the operation failed                                                    | str                     |
| payload      | The raw event Exa delivered                                                              | Dict\[str, Any]         |
| event\_type  | The event, e.g. monitor.run.completed                                                    | str                     |
| event\_id    | Unique ID of this event                                                                  | str                     |
| created\_at  | When the event happened (ISO 8601)                                                       | str                     |
| monitor\_id  | The monitor the event is about                                                           | str                     |
| run\_id      | The run's ID (run events only)                                                           | str                     |
| status       | Run status for run events (completed, failed, ...), or monitor status for monitor events | str                     |
| results      | New search results found by the run                                                      | List\[Dict\[str, Any]]  |
| result       | Each result, one at a time                                                               | Dict\[str, Any]         |
| content      | Synthesized findings: text, or JSON matching the monitor's output schema                 | Content                 |
| grounding    | Citations and confidence for each synthesized field                                      | List\[MonitorGrounding] |
| fail\_reason | Why the run failed; empty unless it failed                                               | str                     |
| run          | The full run                                                                             | Run                     |
| monitor      | The monitor (monitor created/updated/deleted events only)                                | Monitor                 |
| metadata     | The monitor's metadata, echoed back by Exa                                               | Dict\[str, str]         |

### Possible use case

**Alerts**: Send each run's new results to Slack or email as soon as the monitor finds them.

**Data Pipeline**: Append every new result to a spreadsheet or database for later analysis.

**Routing by Metadata**: Use the echoed metadata to send results from many monitors to the right team or client.

***


---

# 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://agpt.co/docs/integrations/block-integrations/search_monitor_trigger.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.
