Prep Data for AI: Verified Answers

When working with Copilot in Power BI, many users are surprised to see different answers returned for the same question. In this training session, Justin Vogel from Pragmatic Works explains why this happens and how data professionals can eliminate ambiguity by preparing their models correctly for AI. The key concept introduced is the use of Verified Answers, a feature designed to make Copilot responses consistent, predictable, and aligned with defined business logic.

Why Copilot Gives Different Answers

Justin begins by demonstrating two nearly identical Power BI reports. Both reports use the same data and the same DAX calculations. However, Copilot behaves very differently in each one. The difference is not randomness or error. It is interpretation.

In an unprepared report, Copilot relies heavily on column names, measure names, and general wording. When users ask questions like “What are total sales?” or “What is our top performing product?”, Copilot attempts to infer meaning. That inference can vary depending on context, wording, or available metadata.

• “Total sales” may match multiple measures.
• “Year-over-year growth” may require Copilot to decide how growth is calculated.
• “Top performing product” could mean revenue, margin, or quantity.

Copilot is not wrong in these scenarios. As Justin explains, it is doing the best it can with the information provided. The problem is that inference introduces inconsistency.

What It Means to Prep Data for AI

To remove ambiguity, Justin introduces the concept of Prep Data for AI in Power BI. One of the most powerful components of this process is Verified Answers.

Verified Answers live in the semantic model within the Power BI service. While the DAX logic that drives accurate results is usually created in Power BI Desktop, Verified Answers are configured after the report is published to a paid Fabric-enabled workspace. This feature does not work in trial environments.

1. Publish the report to a paid Fabric-enabled workspace.
2. Open the semantic model in the Power BI service.
3. Navigate to Prep Data for AI.
4. Select Verified Answers.

Defining Verified Answers in a Report

Once inside the semantic model, Power BI guides users back to the report itself. Justin demonstrates how to define a verified answer by right-clicking on a visual in the report.

In the example, a visual shows the highest-selling product, which is calculated using an existing DAX measure. Instead of allowing Copilot to guess what “best-selling product” means, Justin explicitly defines that visual as the answer.

Power BI automatically suggests related questions, such as:

• What is our best selling product?
• Which product sells the most?
• What is our bestselling product?

These suggested phrases can be added to the verified answer. Once applied, any question that closely matches these phrases will return the predefined visual as the response.

Verified Answers vs Measure Descriptions

Justin makes an important distinction between measure descriptions and verified answers.

• Measure descriptions help Copilot better understand what a calculation represents.
• They improve the probability of correct interpretation.
• Verified answers define the response itself.
• They remove interpretation entirely.

In Justin’s words, descriptions improve probability, while verified answers create certainty.

Seeing the Impact on Copilot

After republishing the report, Justin revisits the Copilot pane and asks the same question: “What is our bestselling product?” This time, Copilot immediately returns the exact visual that was defined as the verified answer. The Copilot pane also confirms that the question matched a verified answer.

In a fully prepared model, even questions like “What are total sales?” return precise values rather than ambiguous explanations. Copilot no longer needs to guess because the business logic has already been defined.

Key Takeaways for Power BI Professionals

Justin concludes with an important message for data professionals. Preparing data for AI is not about making Copilot smarter. Copilot is already powerful. The goal is to make the model clearer.

• If business logic is not defined, Copilot will infer it.
• If business logic is defined, Copilot becomes predictable.
• Copilot does not replace data modeling.
• Copilot amplifies the quality of the model.

By understanding how Copilot reads and interacts with a semantic model, users gain control over that amplification. Verified Answers ensure consistency, trust, and confidence in AI-driven insights.

For more guidance on Copilot, Fabric, and AI in Power BI, Pragmatic Works offers additional videos, on-demand learning, and consulting services to help organizations succeed.