Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Within an eventhouse, Copilot can generate a Real-Time Dashboard for a selected database based on the tables it contains. This capability helps you quickly start analyzing trends and anomalies in streaming data.
Describe the insights you want in natural language, and Copilot creates a dashboard tailored to your selected data and goal.
For billing information about Copilot, see Announcing Copilot in Fabric pricing.
Prerequisites
Note
- Your administrator needs to enable the tenant switch before you start using Copilot. See the article Copilot tenant settings for details.
- Your F2 or P1 capacity needs to be in one of the regions listed in this article, Fabric region availability.
- If your tenant or capacity is outside the US or EU, Copilot is disabled by default. Your Fabric tenant admin will also need to enable the Data sent to Azure OpenAI can be processed outside your capacity's geographic region, compliance boundary, or national cloud instance tenant setting in OneLake catalog > Govern > Configurations > Tenant settings to use Copilot.
- Copilot in Microsoft Fabric isn't supported on trial SKUs. Only paid SKUs (F2 or higher, or P1 or higher) are supported.
- See the article Overview of Copilot in Fabric and Power BI for more information.
Create a dashboard with Copilot from an eventhouse
Go to the home page of the eventhouse that contains the data you want to visualize.
In the upper ribbon, under New Real-Time Dashboard, select Generate with Copilot.
In the Copilot pane, describe the dashboard you want. Include your goal, the data to prioritize, and how you want the dashboard organized. Use the data-specific example prompts to help you get started.
When analyzing your request, Copilot provides its thought process in the pane. You can follow along to see how Copilot interprets your request.
After Copilot generates a response, you can refine your prompt with follow-up requests to adjust the scope or focus of the dashboard, or select Start dashboard creation to proceed.
Enter a name and location for the dashboard, and then select Create.
Once generated, update the dashboard by adjusting visual types or modifying queries as needed. You can use Copilot to assist with editing visuals or with writing queries.
Save your changes when the dashboard reflects the insights you want to monitor.
Create a dashboard with Copilot from a KQL Queryset
Go to the KQL Queryset that contains the data you want to visualize.
In the upper ribbon, select Generate with Real-Time Dashboard.
In the Copilot pane, describe the dashboard you want. Include your goal, the data to prioritize, and how you want the dashboard organized. Use the data-specific example prompts to help you get started.
When analyzing your request, Copilot provides its thought process in the pane. You can follow along to see how Copilot interprets your request.
After Copilot generates a response, you can refine your prompt with follow-up requests to adjust the scope or focus of the dashboard, or select Start dashboard creation to proceed.
Enter a name and location for the dashboard, and then select Create.
Once generated, update the dashboard by adjusting visual types or modifying queries as needed. You can use Copilot to assist with editing visuals or with writing queries.
Save your changes when the dashboard reflects the insights you want to monitor.