Microsoft AI-901 Online Practice Questions and Exam Preparation

Microsoft AI-901 Online Questions & Answers

• Question 31:

  You need an AI workload that creates a new product description from a short user prompt.

  Which AI capability does this describe?

  A. generative AI
  B. speaker recognition
  C. optical character recognition
  D. sentiment analysis
  A. generative AI

• Question 32:

  Which two purposes can instructions serve when you create prompts or configure an agent? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. define response constraints
  B. select the Azure region where inference runs
  C. define the role and behavior to follow
  D. increase the model token quota
  E. store extracted invoice fields
  A. define response constraints
  C. define the role and behavior to follow

• Question 33:

  HOTSPOT

  You are learning how generative AI models are trained and used in production environments.

  For each of the following statements about generative AI models, select Yes if the statement is true.

  Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

• Question 34:

  A company wants an AI system to avoid unfair outcomes for users from different demographic groups.

  Which Microsoft responsible AI principle addresses this requirement?

  A. Transparency
  B. Fairness
  C. Accountability
  D. Inclusiveness
  B. Fairness

• Question 35:

  HOTSPOT

  You are designing prompts for a generative AI application that uses a large language model (LLM).

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

  NOTE: Each correct selection is worth one point.

  

  

• Question 36:

  Your company processes customer support emails.

  You need to implement an AI solution that automatically identifies mentions of people, organizations, and locations in the emails.

  Which text analysis technique should you use?

  A. sentiment analysis
  B. Named Entity Recognition (NER)
  C. summarization
  D. key phrase extraction
  B. Named Entity Recognition (NER)

• Question 37:

  You are developing an application that extracts fields from PDFs by using Azure Content Understanding in Foundry Tools.

  You need to use the Python SDK to submit a PDF for analysis and retrieve the extraction results.

  What should you do?

  A. Call begin_analyze(), and then call poller.result() to retrieve the results.
  B. Submit the PDF to an analyzer and read the results from the request headers.
  C. Use optical character recognition (OCR) to extract text from the PDF and map the fields in the code.
  D. Call analyze() to return the extracted fields synchronously in the same request.
  A. Call begin_analyze(), and then call poller.result() to retrieve the results.

• Question 38:

  HOTSPOT

  You are creating an AI agent in Microsoft Foundry that will answer questions and perform tasks on behalf of users.

  To define the agent's role, behavior, instructions, and response style, you must configure a _______ for the agent.

  Select the answer that correctly completes the sentence.

  

  

• Question 39:

  DRAG DROP

  You are developing an application that extracts structured information from different types of content by using Azure Content Understanding in Foundry Tools.

  You need to extract scanned invoices in the PDF format and voicemail recordings in the WAV format.

  Which type of analyzer should you use for each content type?

  To answer, drag the appropriate analyzer types to the correct content types.

  Each analyzer type may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.

  NOTE: Each correct selection is worth one point.

  Select and Place:

  

  

• Question 40:

  You are designing prompts for a generative AI app. You need to set the model role, tone, and response constraints for all user requests.

  What should you configure?

  A. a system prompt
  B. a region setting
  C. a token quota
  D. an image URL
  A. a system prompt