> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getbluejay.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Watch Your Agent After Hours

> Get paged when your agent breaks after hours.

Set up an [uptime monitor](/monitor/uptime/overview.md) that calls your agent every 10 minutes around the clock and pages your on-call team when it stops answering or starts stating errors.

<video controls muted playsInline preload="metadata" src="https://mintcdn.com/bluejay/dF8I5qGAanSDLxfr/videos/cookbook-after-hours-uptime-walkthrough.mp4?fit=max&auto=format&n=dF8I5qGAanSDLxfr&q=85&s=572eb2c99fbc462a6c7208b09d7ecc1d" />

## Before you start

* Connect PagerDuty or Better Stack, so the alert reaches whoever is on call. See [Alerts](/monitor/alerts.md#connect-a-channel).
* If your agent only makes outbound calls, set it up to start a call when Bluejay asks. See [Outbound agents](/monitor/uptime/overview.md#outbound-agents).

## Steps

**1. Open the create dialog**

In **Observability → Uptime**, click **Create**.

![The New Uptime Monitor dialog with an agent chosen, Frequency set to Every 10 minutes, Runs on set to Always, and the health checks listed](https://mintcdn.com/bluejay/UqiH6o220FskMm0H/images/cookbook-after-hours-create-dialog.png?fit=max\&auto=format\&n=UqiH6o220FskMm0H\&q=85\&s=5286cad3b225eb8167c24c19c4bdebbe)

**2. Run it around the clock**

Pick your agent, then set **Frequency** to **Every 10 minutes**. The default is every 5 minutes, and checking more often than that can significantly raise your costs.

Leave **Runs on** at **Always**. A monitor has one schedule, made of its days and one range of hours, so **Always** is the only way to cover both nights and weekends.

**3. Keep the health checks on**

Keep **Agent Malfunction** and **Agent Responds** on, so an agent that states an error or stops answering counts as a failure. See [Checks](/monitor/uptime/overview.md#checks).

**4. Send failures to your on-call tool**

Click **Next**, then turn on **PagerDuty Notifications** or **Better Stack Notifications**. A channel that is not connected cannot be turned on, and the dialog links to its setup. Your escalation policy in that tool decides who gets paged. See [Incidents](/monitor/alerts.md#incidents).

![Step 2 of 2 of the New Uptime Monitor dialog with PagerDuty Notifications turned on and Slack, Better Stack, and email off](https://mintcdn.com/bluejay/UqiH6o220FskMm0H/images/cookbook-after-hours-notifications.png?fit=max\&auto=format\&n=UqiH6o220FskMm0H\&q=85\&s=b91c8f3ac55d9c2f67927abddea3d64b)

**5. Create the monitor**

Click **Create**. The first check starts right away.

![The Uptime page with fleet uptime, active monitors, and incidents for the last 7 days, above one row for each monitor showing its agent, status such as Operational, Down, or Paused, uptime, frequency, incidents, and last check](https://mintcdn.com/bluejay/eKcFBkjZX47pI8Ss/images/uptime-monitors-list.png?fit=max\&auto=format\&n=eKcFBkjZX47pI8Ss\&q=85\&s=144dd67a421f4e34837ba8a95cd8e107)

## Check the result

Each run gets one of these verdicts:

* **Up** means all checks passed.
* **Down** means at least one check failed. Bluejay opens an incident in PagerDuty or Better Stack, and resolves it when the monitor recovers.

If the first run is **Down**, open it to see which check failed, and read the transcript before you rely on the monitor overnight.

![A Down check run with Agent Responds marked Down because the agent did not connect, Latency marked Unknown, and the run's completion time](https://mintcdn.com/bluejay/UqiH6o220FskMm0H/images/cookbook-after-hours-uptime-down-run.png?fit=max\&auto=format\&n=UqiH6o220FskMm0H\&q=85\&s=1a3183f6cb6e497a36dd4682f2957176)

## Related

* [Uptime Monitoring](/monitor/uptime/overview.md)
* [Alerts](/monitor/alerts.md)
* [Uptime Monitoring API](/api-reference/endpoint/create-uptime-monitor.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.