Monitors Quickstart
To better understand your model monitoring needs, we suggest using the 'Performance Tracing' tab or the 'Drift' tab to identify insights relevant to your model. This will help inform what monitors to create and what modifications you need to make to your monitor.
Follow Step 2 in our quickstart guide to get started finding model insights!
Based on the insights you discover, create monitors to keep an eye on key performance, drift, and data quality metrics. Navigate to the 'Monitors' tab and enable relevant preset monitors for your use case.
If you only want to monitor specific features and dimensions, create a custom monitor. Learn more here.
Enable Managed Monitors From the monitors 'Setup' tab
Managed monitors create monitors for all applicable features for a given metric with preset basic configurations and an automatic threshold. Based on the metric and feature monitor you want to edit, edit your monitors details.
Evaluation Window: The period of time your metric is calculated on (i.e. the previous 30 days). Increase this window to smooth out spiky or seasonal data. Decrease this for your monitors to react faster to sudden changes.
Delay window: Change this if you have delayed actuals or predictions, so you evaluate your model on the most up-to-date data.
Edit Evaluation Window
You can use our dynamic automatic threshold or create a custom threshold. Thresholds trigger notifications, so you can adjust your threshold to be more or less noisy depending on your needs. Learn more about thresholds here.
Get notified when your model deviates from your threshold. You can send notifications via e-mail, PagerDuty, OpsGenie, or Slack. Learn more about notifications and integrations here.
Enable Notifications