Overview

​

What is a Dashboard?

A Dashboard provides a clear view of your AI application performance, whether over time or across multiple experiments and tests.

Each Project has a Dashboard. It’s empty at first. To populate it, you need to run an evaluation and save at least one Report to the Project. You can then choose values from Reports to plot.

You can use the Dashboard to track live production quality or results from offline experiments.

The “Show in order” toggle lets you switch between two views:

• Time Series. Displays data with actual time intervals, ideal for live monitoring.

• Sequential. Shows results in equal spacing, perfect for experiments.

All Panels in a Dashboard reflect the date range set by the time range filter. You can zoom in on any time series visualization for detailed analysis.

​

Dashboard Panels

A Panel is a visual element in the Dashboard that displays specific values or test results. Panels can be counters, line plots, bar plots, etc.

You can customize your Dashboard by adding Panels:

• Using Python API. Define dashboard as code.

• Through the UI. Add Panels directly from the interface. (Cloud and Enterprise only).

To create a Panel, you need to specify:

• Value. You can plot both Metrics (e.g., drift score) or Test results (e.g., Pass/Fail).

• Parameters like type, size, and title.

• Tags (optional). You can filter and visualize specific data subsets. To enable this, you must first add Tags (e.g. a model version) to Reports when you run an evaluation.

​

From Dashboard to Reports

By clicking on any individual value on the Dashboard, you can open the associated Report and source Dataset for further debugging.

​

Using Tabs

You can logically organize Panels within the same Dashboard into different Tabs.

Pre-built Tabs. To simplify setup, you can start with dashboard templates for common use cases.