Microsoft AI-901 Online Practice Questions and Exam Preparation

Microsoft AI-901 Online Questions & Answers

• Question 11:

  HOTSPOT

  You are configuring an AI agent in Microsoft Foundry Agent Service. The agent can optionally invoke tools to complete tasks.

  For each of the following statements, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

• Question 12:

  You have a Microsoft Foundry project that has a generative AI model deployment.

  You need to ensure that responses generated by the model minimize costs and remain within a defined length.

  Which parameter should you configure?

  A. Temperature
  B. Max Completion Tokens
  C. Top P
  D. Model version settings
  B. Max Completion Tokens

• Question 13:

  You need to build an AI solution that generates marketing email drafts based on a short description of a product and its target audience.

  Which AI workload should you use?

  A. generative AI
  B. computer vision
  C. text classification
  D. speech recognition
  A. generative AI

• Question 14:

  HOTSPOT

  You are designing an AI agent that uses a generative AI model to determine actions and responses based on user requests.

  For each of the following statements about AI agents and generative AI models, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

• Question 15:

  You are creating a single-agent solution in the Foundry portal. You need the agent to follow a support-specialist role and stay within support-policy boundaries.

  What should define the agent behavior?

  A. agent instructions
  B. a document extraction schema
  C. a speech voice name
  D. a computer vision label
  A. agent instructions

• Question 16:

  You are developing an AI-powered customer support application.

  Which task is an example of the Microsoft responsible AI principle of inclusiveness?

  A. Provide explanations about how predictions are generated.
  B. Design the interface to support multiple languages and screen readers.
  C. Evaluate model outputs across demographic groups to reduce bias.
  D. Encrypt stored customer data and restrict access by using role-based controls.
  B. Design the interface to support multiple languages and screen readers.

• Question 17:

  HOTSPOT

  Your organization plans to deploy foundation models from the Microsoft Foundry model catalog.

  For each of the following statements about model deployment and testing in Microsoft Foundry, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

• Question 18:

  A production AI feature must continue to be reviewed after release so unexpected failures can be detected and corrected.

  Which practice best supports this requirement?

  A. ongoing monitoring and improvement
  B. removing human oversight after deployment
  C. using a system prompt to replace access control
  D. selecting a model only by name
  A. ongoing monitoring and improvement

• Question 19:

  HOTSPOT

  You are developing a voice application that listens for spoken commands and converts them into text by using Azure Speech in Foundry Tools.

  How should you complete the Python code? To answer, select the appropriate option in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

• Question 20:

  Your company has thousands of recorded customer support calls in multiple languages stored as audio files in Azure Storage.

  You need to generate text transcripts of all the recordings.

  Which Azure Speech in Foundry Tools capability should you use?

  A. speech to text batch transcription
  B. speech to text real-time transcription
  C. text to speech
  D. speech translation
  A. speech to text batch transcription