Microsoft Building Intelligent Applications - AB-410 Exam Practice Test

A developer needs an AI model to classify incoming emails into categories such as billing, technical support, and complaints. The categories are predefined and training examples are available. Which machine learning approach is appropriate?

A company uses Dataverse to configure derived values for sales records.
The company requires the following functionality:
- Evaluate an expression by using numerical columns in the same row.
- Calculate the result dynamically when accessed.
- Ensure the result is NOT stored as part of the table data.
- The solution must minimize use of custom code.
You need to configure the app.
What should you do?

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result these questions will not appear in the review screen.
You administer the Microsoft 365 and Microsoft Power Platform environments for Contoso, Ltd.
The company has a model-driven app that is used to track customer interactions with employees.
The app uses standard table types for customers. A user named Elisabeth Rice signs in to the app by using the following sign in name: [email protected].
After marriage, Elisabeth changes her legal name to Elisabeth Mueller.
You need to update the sign in name for the user without losing any application history.
Solution: From Dynamics 365 Settings, select Email Configuration. In the active mailbox for the user, update the name.
Does the solution meet the goal?

A company is using Microsoft Dataverse.
You must integrate Dataverse with a third-party AI service. The solution requires authentication and custom request handling to send and receive data.
You need to enable the integration.
What should you do?

A development team wants to improve an AI application's responses by providing specific instructions about tone, role, and expected behavior. Which prompt component should be used?

A company tracks order processing duration using a model-driven app.
The company requires a system that provides the following functionality:
- The age of the order, based on the created date, must be displayed on forms and views.
- The value must update dynamically when viewed without storing the
result.
- The value must NOT be stored in the database.
You need to configure the column types.
Which two column types should you use? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.

A company is building a prompt about product specifications. The company plans to use the prompt in Power Automate.
The prompt must use Retrieval-Augmented Generation to ground the model with additional business information.
You need to select the available knowledge source for the prompt.
What should you use?

A company wants to build a generative AI assistant that answers employee questions using internal policies stored in SharePoint. The assistant must provide responses based only on approved company documents. Which architecture pattern should be implemented?

A company builds a canvas app that processes images submitted by users and must classify them using an existing AI Builder model.
The app must generate predictions during user interaction.
You need to consume the AI model natively.
What should you do?

A company uses a Dataverse table to manage support cases.
You must provide employees with a summary of case information derived from multiple columns without requiring a manual review of the data.
The solution has the following requirements:
- Generate a case summary following the given instructions.
- Include the context of the current record in the generated output.
You need to configure the solution.
Which two actions should you perform? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.