Microsoft AI-901 Online Practice Questions and Exam Preparation

Microsoft AI-901 Online Questions & Answers

• Question 61:

  Which two tasks are examples of common text analysis techniques? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. extracting key phrases from customer feedback
  B. creating a model deployment endpoint
  C. detecting named entities in an email
  D. choosing a speech synthesis voice
  E. generating a new image from a prompt
  A. extracting key phrases from customer feedback
  C. detecting named entities in an email

• Question 62:

  HOTSPOT

  You are building a content analysis solution by using Azure Content Understanding in Foundry Tools.

  The solution must identify specific fields such as invoice number, vendor name, total amount, and invoice date from submitted documents.

  _______ defines which fields to extract when analyzing content.

  Select the answer that correctly completes the sentence.

  

  

• Question 63:

  A manager wants a short version of a long meeting transcript.

  Which text analysis technique should be used?

  A. summarization
  B. named entity recognition
  C. language detection
  D. key phrase extraction
  A. summarization

• Question 64:

  You have a Microsoft Foundry project that contains a vision-enabled model deployment.

  You are developing an application that sends images to the model. You need to ensure that the model can analyze the images.

  In which two formats can you provide the images? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. a JSON document that describes the image content
  B. a UTF-8 encoded text description of the image
  C. a publicly accessible URL of the image
  D. a base64 encoded image data string
  C. a publicly accessible URL of the image
  D. a base64 encoded image data string

• Question 65:

  HOTSPOT

  You are deploying a generative AI model in Microsoft Foundry and preparing applications to consume the deployed endpoint.

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

  NOTE: Each correct selection is worth one point.

  

  

• Question 66:

  You deploy a model that can process images and text. An app must ask questions about a submitted product photo.

  Which workload capability is required?

  A. speech recognition
  B. a multimodal model that can interpret visual input
  C. key phrase extraction
  D. speaker verification
  B. a multimodal model that can interpret visual input

• Question 67:

  DRAG DROP

  You have a Microsoft Foundry project named project1 that contains an Azure OpenAI resource named Resource1.

  To Resource1, you deploy a gpt-4.1-mini model by using a model deployment named my-mini-gpt.

  You need to connect to my-mini-gpt from an application.

  How should you complete the Python code? To answer, drag the appropriate values to the correct targets.

  Each value may be used once, more than once, or not at all.

  NOTE: Each correct selection is worth one point.

  Select and Place:

  

  

• Question 68:

  HOTSPOT

  You need to build an AI solution that generates marketing images, product descriptions, and other new content based on prompts entered by users.

  Which AI workload should you use?

  Select the answer that correctly completes the sentence.

  

  

• Question 69:

  You are developing a web app that processes invoices to calculate expenses.

  You need to extract structured fields, including nested values, from the invoices by using a defined schema.

  What should you use?

  A. a transcription workflow in Azure Speech in Foundry Tools
  B. an optical character recognition (OCR)-only document processing pipeline
  C. an analyzer in Azure Content Understanding in Foundry Tools
  D. an Azure AI Search service
  C. an analyzer in Azure Content Understanding in Foundry Tools

• Question 70:

  HOTSPOT

  Your organization is implementing Responsible AI practices for a generative AI solution that will be used in production.

  For each of the following statements about accountability in Responsible AI, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.