Relic Solution: View your Superwise ML models performance in New Relic One and increase team collaboration

Gain machine learning (ML) observability and monitor your models in New Relic One with Superwise data and insights for a centralized operational view of your ML applications to seamlessly collaborate between data science and DevOps teams to achieve great outcomes. is a model management platform for ML at high-scale with features that include automated KPIs, incidents management, and model customization builder to deliver critical insights out-of-the-box.

Learn more about Superwise data integration here.

How to Integrate New Relic with Superwise

What you’ll get

Follow the instructions to get instant observability for your machine learning models in production. You’ll get:

  • A guided integration set up for Superwise
  • A pre-built dashboard with charts to help you monitor your models

What you’ll need

Before you begin, ensure you have a New Relic account, or sign up for a free account here (no credit card needed).

You will also need to have a Superwise account. You can get one here.

Quickstart for Superwise: Insights in minutes

If you have already set up the Superwise MLOps integration for New Relic and just want to get the dashboard, install this quickstart from New Relic I/O. Otherwise, read on for all the steps.

To quickly see your data in a pre-built dashboard, it’s as easy as 1-2-3:

  1. Click “Install this quickstart”

  2. Select “skip this step” in the installation plan. (Clicking begin installation will bring you through the integration installation)

  3. After that, you should be able to see your Superwise data in a pre-built dashboard!

Set up the integration

If you haven’t yet set up the Superwise integration, follow these steps:

  1. Log in to, go to Explorer and select + Add more data.

New Relic product screen capture

  1. Scroll down to the MLOps Integration section and select Superwise.

Superwise integration highlighted on New Relic integrations screen.

  1. Select your New Relic account ID.
  2. You need to create two access tokens. First, select Create a Key under Model metric data. Then select Create a Key under Incidents. Make sure the keys are available for future steps.

Buttons to create keys in Superwise integration setup are highlighted in image.

  1. Log in to the Superwise portal and go to notification channel settings. Select New Relic and create a channel name.
  2. Using the two tokens you created in step 4, paste the API key under Incident Intelligence API and the Insight key under Telemetry Key in the Superwise portal.
  3. Test both tokens for verification and select Save.
  4. In the New Relic integration dashboard, select See your data. This will redirect you to an automatically generated New Relic dashboard powered by Superwise.

See your data button in Superwise integration setup screen highlighted.

  1. Superwise’s dashboard contains three charts: the Model Activity chart, the Model Input Drift detection chart, and the Incident Insights chart.

Superwise dashboard

  1. Set up New Relic policies and conditions based on your ML Model metrics by creating an alert condition. To do so, select the three dots on any metric chart in your dashboard and choose Create alert condition from the dropdown.

Create alert condition highlighted in dropdown menu.

  1. Next, set up your notification channels to receive alerts.

Choose pathways to determine where you want to received correlated issues.

  1. You can also correlate your incidents to reduce noise and create custom decisions by training your ML model.

Related activity highlighted in New Data Drift alert for correlating incidents.

You’ve now successfully integrated Superwise with New Relic One. Newly created alerts will now be correlated with your New Relic alerts and you should be able to see data about newly model activity, model input drift, incident insights, and more.

Happy Monitoring!


For more information about this integration, follow the New Relic Docs. For support with setting up your Superwise account, please reach out to

About Superwise allows you to gain visibility in your ML models and scale with confidence with a production first approach, you can define more data-driven retraining strategies and gain the granular insights you need to design better models.