> 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_monitors.md).

# Exa Search Monitors

Blocks for creating Exa Search Monitors that re-run a search on a schedule and post new results to a webhook.

## Exa Create Search Monitor

### What it is

Create an Exa Search Monitor that re-runs a search on a schedule and posts only new results to a webhook (pair it with the Exa Search Monitor Trigger block)

### How it works

This block sends a single `POST /monitors` request to Exa and returns as soon as the monitor exists; it does not wait for the first run. Each later run (on the `period` schedule, or when started with Exa Trigger Search Monitor) happens on Exa's side, drops results earlier runs already returned, and posts the outcome to `webhook_url`. If Exa's response reports a `costDollars` total, the block bills it at 150 credits per USD; otherwise the call is free. Scheduled runs are not billed through this block, so it needs your own Exa API key and fails with a clear message on the platform's shared Exa key, which every user shares as one Exa account.

`webhook_url` must not be blank, and `period` must be a whole number followed by `h` or `d` (for example `6h`, `1d` or `7d`; mixed units like `1d12h` are rejected). The period defaults to `1d`; clear it to create a manual-only monitor. Content options that only `/search` supports, such as `snapshotAsOf` or a summary JSON schema, are dropped. The one-time `webhook_secret` is returned only here: paste it into the Exa Search Monitor Trigger block so deliveries are verified.

### Inputs

| Input            | Description                                                                                                                                                                                                                                                                | Type                                                                                                                   | Required |
| ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | -------- |
| query            | What to watch for. Describe the ongoing signal rather than adding dates: each run only reports results that are new.                                                                                                                                                       | str                                                                                                                    | Yes      |
| webhook\_url     | HTTPS URL Exa posts each run to. To handle runs in a workflow, add an 'Exa Search Monitor Trigger' block to it, save, and paste that block's webhook URL here. Must be publicly reachable (no localhost or private IPs); redirects are not followed.                       | str                                                                                                                    | Yes      |
| period           | How often the monitor runs: a whole number followed by h (hours) or d (days), minimum 1h, e.g. 6h, 1d or 7d. The schedule is anchored to the creation time and a run may start up to 30 minutes late. Leave empty for a manual-only monitor that runs only when triggered. | str                                                                                                                    | No       |
| name             | Optional display name for the monitor                                                                                                                                                                                                                                      | str                                                                                                                    | No       |
| num\_results     | Search results to fetch per run (1-100)                                                                                                                                                                                                                                    | int                                                                                                                    | No       |
| include\_domains | Only return results from these domains                                                                                                                                                                                                                                     | List\[str]                                                                                                             | No       |
| exclude\_domains | Never return results from these domains                                                                                                                                                                                                                                    | List\[str]                                                                                                             | No       |
| contents         | Page content to attach to each result (text, highlights, summary, livecrawl and more)                                                                                                                                                                                      | ContentSettings                                                                                                        | No       |
| output\_schema   | Format of each run's synthesized output. Defaults to {"type": "text"} (a plain-text summary). Use {"type": "object", "properties": {...}} for JSON matching your schema; citations are returned separately in grounding, so leave them out of the schema.                  | Dict\[str, Any]                                                                                                        | No       |
| metadata         | Key-value pairs echoed back in every webhook delivery, useful for routing results                                                                                                                                                                                          | Dict\[str, str]                                                                                                        | No       |
| webhook\_events  | Events to post to the webhook. Leave empty to receive all of them (lifecycle, run started and run completed).                                                                                                                                                              | List\["monitor.created" \| "monitor.updated" \| "monitor.deleted" \| "monitor.run.created" \| "monitor.run.completed"] | No       |

### Outputs

| Output          | Description                                                                                                                                                              | Type    |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------- |
| error           | Error message if the operation failed                                                                                                                                    | str     |
| monitor\_id     | The new monitor's ID                                                                                                                                                     | str     |
| webhook\_secret | Secret for verifying this monitor's webhook deliveries. Exa shows it only once: paste it into the Exa Search Monitor Trigger block's webhook secret, or store it safely. | str     |
| status          | Monitor status, normally active                                                                                                                                          | str     |
| next\_run\_at   | When the first scheduled run happens (ISO 8601); empty for a manual-only monitor                                                                                         | str     |
| monitor         | The full monitor                                                                                                                                                         | Monitor |

### Possible use case

**Competitor Watch**: Get a daily webhook with only the new pages announcing a competitor's product launches or pricing changes.

**Regulatory Tracking**: Watch government and agency domains for new rulings on a topic and route them to a review workflow using metadata.

**Market Signals**: Run a weekly monitor with an output schema that turns each run's new articles into structured fields such as company, location and investment size.

***


---

# 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_monitors.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.
