Blog Post

Copilot in Microsoft Fabric


Microsoft Copilot is an app that uses AI to help you find information, create content, and get things done faster (see What Is Copilot? Microsoft’s AI Assistant Explained).  Copilot is now integrated heavily in Microsoft Fabric to bring new ways to transform and analyze data, generate insights, and create visualizations and reports in Microsoft Fabric and Power BI. I wanted to cover the places you will find Copilot in Fabric.

First you need to enable Copilot. Note that Copilot in Microsoft Fabric is rolling out in stages with the goal that all customers with a paid Fabric capacity (F64 or higher) or Power BI Premium capacity (P1 or higher) have access to Copilot. It becomes available to you automatically as a new setting in the Fabric admin portal when it’s rolled out to your tenant. When charging begins for the Copilot in Fabric experiences, you can count Copilot usage against your existing Fabric or Power BI Premium capacity.

See the article Overview of Copilot in Fabric for answers to your questions about how it works in the different workloads, how it keeps your business data secure and adheres to privacy requirements, and how to use generative AI responsibly.

The spots you will find Copilot in Fabric:

Copilot for Power BI – Quickly create report pages, natural language summaries, and generate synonyms. As a report author, you can use Copilot to help you write DAX queries, streamline your semantic model documentation, provide a summary about your semantic model, and help you get started with report creation by suggesting topics based on your data. Additionally, Copilot can also create a narrative visual that summarizes a page or a whole report and can generate synonyms for Q&A, to help report readers find what they’re looking for in your reports. You can also ask specific questions about the visualized data on a report page and receive a tailored response. This response includes references to specific visuals, aiding you in understanding the specific data sources contributing to each part of the answer or summary within the report.

Copilot for Data Factory (in preview) – Get intelligent code generation to transform data with ease and code explanations to help you better understand complex tasks. Copilot works with Dataflow Gen2 to: generate new transformation steps for an existing query, provide a summary of the query and the applied steps, and generate a new query that may include sample data or a reference to an existing query.

Copilot for Data Science and Data Engineering (in preview) – Quickly generate code in Notebooks to help work with Lakehouse data and get insights. Copilot for Data Science and Data Engineering is an AI assistant that helps analyze and visualize data. It works with Lakehouse tables and files, Power BI Datasets, and pandas/spark/fabric dataframes, providing answers and code snippets directly in the notebook.  The most effective way of using Copilot is to add your data as a dataframe. You can ask your questions in the chat panel, and the AI provides responses or code to copy into your notebook. It understands your data’s schema and metadata, and if data is loaded into a dataframe, it has awareness of the data inside of the data frame as well. You can ask Copilot to provide insights on data, create code for visualizations, or provide code for data transformations, and it recognizes file names for easy reference. Copilot streamlines data analysis by eliminating complex coding.

Copilot for Data Warehouse – Write and explain T-SQL queries, or even make intelligent suggestions and fixes while you are coding. Key features of Copilot for Warehouse include:

  • Natural Language to SQL: Ask Copilot to generate SQL queries using simple natural language questions.
  • Code completion: Enhance your coding efficiency with AI-powered code completions.
  • Quick actions: Quickly fix and explain SQL queries with readily available actions.
  • Intelligent Insights: Receive smart suggestions and insights based on your warehouse schema and metadata.

    There are three ways to interact with Copilot in the Fabric Warehouse editor.

  • Chat Pane: Use the chat pane to ask questions to Copilot through natural language. Copilot will respond with a generated SQL query or natural language based on the question asked.
  • Code completions: Start writing T-SQL in the SQL query editor and Copilot will automatically generate a code suggestion to help complete your query. The Tab key accepts the code suggestion, or keep typing to ignore the suggestion.
  • Quick Actions: In the ribbon of the SQL query editor, the Fix and Explain options are quick actions. Highlight a SQL query of your choice and select one of the quick action buttons to perform the selected action on your query.
    • Explain: Copilot can provide natural language explanations of your SQL query and warehouse schema in comments format.
    • Fix: Copilot can fix errors in your code as error messages arise. Error scenarios can include incorrect/unsupported T-SQL code, wrong spellings, and more. Copilot will also provide comments that explain the changes and suggest SQL best practices.
    • How to: Use Copilot quick actions for Synapse Data Warehouse

Copilot for Real-Time Intelligence (in preview) – Copilot for Real-Time Intelligence lets you effortlessly translate natural language queries into Kusto Query Language (KQL). The copilot acts as a bridge between everyday language and KQL’s technical intricacies, and in doing so removes adoption barriers for citizen data scientists.

Check out Copilot for Fabric Consumption for information on how the Fabric Copilot usage is billed and reported.

Copilot is a fantastic accelerator for building solutions and you can expect to see more of Copilot in Fabric in the near future!

More info:

Copilot in Power Query in Power BI Service and Microsoft Fabric Dataflow Gen2

Exploring the Potential and Pitfalls of Microsoft Fabric Copilot: A Practical Analysis

How to Use Power BI Copilot in Microsoft Fabric

The post Copilot in Microsoft Fabric first appeared on James Serra's Blog.

Original post (opens in new tab)
View comments in original post (opens in new tab)


You rated this post out of 5. Change rating




You rated this post out of 5. Change rating