Revizo / Microsoft / AI-901

MICROSOFT CERTIFICATION STUDY GUIDE

AI-901 practice questions.
Prepare with a clearer plan.

Validates foundational knowledge of AI concepts and capabilities, and the ability to implement AI solutions using Azure and Microsoft Foundry.

Download Revizo
Revizo certification practice question on iPhone

What to know about AI-901.

Validates foundational knowledge of AI concepts and capabilities, and the ability to implement AI solutions using Azure and Microsoft Foundry.

Format
Multiple choice questions
Duration
45 minutes
Passing score
700/1000
Recommended experience
Conceptual knowledge of AI solutions in Azure; basic Python and Azure familiarity helpful

Exam details are based on the available Microsoft catalogue information. Confirm current requirements with the exam provider before booking.

How to prepare for AI-901.

Use the provider's current objectives as your source of truth, then organise your Revizo sessions around the Microsoft technologies, product capabilities and implementation decisions named in the certification. The AI-901 exam is listed as Multiple choice questions; your starting point should reflect Conceptual knowledge of AI solutions in Azure; basic Python and Azure familiarity helpful.

01

Map the official objectives.

Read the current Microsoft objectives and make a short list of the areas you need to revisit before booking AI-901.

02

Practise one area at a time.

Select AI-901 in Revizo and use focused question sessions to test one topic or decision type at a time, rather than relying on a single long cram session.

03

Review, then repeat.

Use your results to return to incorrect answers, revisit the official material behind them and repeat short AI-901 practice sessions until the gaps are clearer.

FREE PRACTICE PREVIEW

Read the first 20
AI-901 questions.

Review each question, its correct answer and any available source explanation before continuing your certification study in Revizo.

FIRST 20 QUESTIONS

Answers & available explanations

QUESTION 1

You are using the Azure Speech SDK to develop a Python application that supports real-time spoken conversations.
Which Azure Speech class should you use to configure the connection to the Azure Speech service?

  1. AA. AudioOutputConfig
  2. BB. SpeechSynthesizer
  3. CC. AudioConfig
  4. DD. SpeechConfig
Show answer & explanation

Correct answer: D

ExplanationSpeechConfig is used to configure subscription key, region, and other connection settings for the Azure Speech SDK.

QUESTION 2

HOTSPOT -
Select the answer that correctly completes the sentence.

    Show answer & explanation

    Correct answer: A

    ExplanationVision-enabled models accept images as base64-encoded image data in the request payload. See Microsoft documentation on using images with the Responses API.

    QUESTION 3

    You need to create an AI agent in Microsoft Foundry that follows a specific role and behavior when responding to users.
    What should you configure?

    1. AA. system instructions
    2. BB. temperature
    3. CC. tokens per minute (TPM)
    4. DD. max completion tokens
    Show answer & explanation

    Correct answer: A

    ExplanationSystem instructions define an agent's role, behavior, and constraints in Microsoft Foundry.

    QUESTION 4

    HOTSPOT -
    For each of the following statements, select Yes if the statement is true. Otherwise, select No.
    NOTE: Each correct selection is worth one point.

    1. ASystem prompts can be used to authorize users.
    2. BA system prompt is used to reduce tokens per minute (TPM).
    3. CA system prompt guides the behavior of a generative AI model.
    Show answer & explanation

    Correct answer: N, N, Y

    ExplanationSystem prompts guide model behavior; they do not handle user authorization or TPM rate limits.

    QUESTION 5

    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?

    1. AA. an optical character recognition (OCR)-only document processing pipeline
    2. BB. a transcription workflow in Azure Speech in Foundry Tools
    3. CC. an analyzer in Azure Content Understanding in Foundry Tools
    4. DD. an Azure AI Search service
    Show answer & explanation

    Correct answer: C

    ExplanationAzure Content Understanding analyzers extract structured fields, including nested values, from documents using a defined schema.

    QUESTION 6

    HOTSPOT -
    For each of the following statements, select Yes if the statement is true. Otherwise, select No.
    NOTE: Each correct selection is worth one point.

    1. AVoice Live returns only transcribed text.
    2. BVoice Live requires you to separately implement speech to text and text to speech services.
    3. CVoice Live combines speech to text, reasoning, and text to speech into a single conversational experience.
    Show answer & explanation

    Correct answer: N, N, Y

    ExplanationVoice Live provides an integrated real-time conversational experience combining STT, model reasoning, and TTS.

    QUESTION 7

    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.

    Item 1

    1. AA. recognizer.recognize_once()
    2. BB. recognizer.speak_text_async("Ready")
    3. CC. recognizer.start_continuous_recognition()
    4. DD. recognizer.start_keyword_recognition()
    Show answer & explanation

    Correct answer: Item 1: C

    ExplanationFor an application that listens for spoken commands, start_continuous_recognition() processes ongoing speech input in real time.

    QUESTION 8

    What are two purposes of instructions when prompting a generative AI model? Each correct answer presents part of the solution.
    NOTE: Each correct selection is worth one point.

    1. AA. defines the agent’s role and behavior
    2. BB. selects which model to use
    3. CC. defines the Azure region where inference occurs
    4. DD. defines the tokens per minute (TPM) allocation for the model
    5. EE. defines constraints on the model’s responses
    Show answer & explanation

    Correct answer: A, E

    ExplanationInstructions define the agent's role/behavior and set constraints on model responses; they do not select models, regions, or TPM allocation.

    QUESTION 9

    HOTSPOT -
    You are developing an application that converts text into spoken audio and saves the synthesized audio to a file 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.

    Item 1

    1. AA. AudioOutputConfig(filename="output.wav")
    2. BB. AudioOutputConfig(stream)
    3. CC. AudioStreamFormat(wave_stream_format=AudioStreamWaveFormat.PCM)
    Show answer & explanation

    Correct answer: Item 1: A

    ExplanationTo save synthesized speech to a file, use AudioOutputConfig with a filename parameter.

    QUESTION 10

    HOTSPOT -
    Select the answer that correctly completes the sentence.

      Show answer & explanation

      Correct answer: D

      ExplanationSystem prompts (system instructions) define an agent's role, behavior, and response guidelines in Microsoft Foundry.

      QUESTION 11

      HOTSPOT -
      You are developing an application that analyze invoices by using Azure Content Understanding in Foundry Tools.
      You need to ensure that the application retrieves the analysis results after processing completes.
      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.

      Item 1

      1. AA. get_results
      2. BB. result
      3. CC. status
      4. DD. wait
      Show answer & explanation

      Correct answer: Item 1: B

      ExplanationAzure SDK long-running operations return a poller; call poller.result() to wait for completion and retrieve analysis results.

      QUESTION 12

      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.

      Item 1

      1. AA. gpt-4.1-mini
      2. BB. my-mini-gpt
      3. CC. project1
      4. DD. resource1

      Item 2

      1. AA. gpt-4.1-mini
      2. BB. my-mini-gpt
      3. CC. project1
      4. DD. resource1
      Show answer & explanation

      Correct answer: Item 1: D · Item 2: B

      ExplanationThe base_url subdomain is the Azure OpenAI resource name (resource1), and the model parameter must be the deployment name (my-mini-gpt), not the underlying model name.

      QUESTION 13

      HOTSPOT -
      For each of the following statements, select Yes if the statement is true. Otherwise, select No.
      NOTE: Each correct selection is worth one point.

      1. AAn AI generative model is retrained before performing each user request.
      2. BAn AI agent responds by copying and pasting answers stored in a database.
      3. CAn AI agent uses a generative AI model to establish actions based on user input.
      Show answer & explanation

      Correct answer: N, N, Y

      ExplanationAgents use pretrained generative models to reason and act; they are not retrained per request and do not simply copy stored answers.

      QUESTION 14

      DRAG DROP -
      You are reviewing best practices for using AI at your company.
      Which Microsoft responsible AI principle is each task an example of? To answer, drag the appropriate principles to the correct tasks. Each task 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 match is worth one point.

      Item 1

      1. AA. Accountability
      2. BB. Fairness
      3. CC. Inclusiveness
      4. DD. Privacy and security
      5. EE. Reliability and safety
      6. FF. Transparency

      Item 2

      1. AA. Accountability
      2. BB. Fairness
      3. CC. Inclusiveness
      4. DD. Privacy and security
      5. EE. Reliability and safety
      6. FF. Transparency

      Item 3

      1. AA. Accountability
      2. BB. Fairness
      3. CC. Inclusiveness
      4. DD. Privacy and security
      5. EE. Reliability and safety
      6. FF. Transparency

      Item 4

      1. AA. Accountability
      2. BB. Fairness
      3. CC. Inclusiveness
      4. DD. Privacy and security
      5. EE. Reliability and safety
      6. FF. Transparency
      Show answer & explanation

      Correct answer: Item 1: B · Item 2: D · Item 3: F · Item 4: E

      ExplanationMicrosoft responsible AI principles: Fairness (bias), Privacy and security (data protection), Transparency (disclosure), Reliability and safety (robust testing).

      QUESTION 15

      HOTSPOT -
      For each of the following statements, select Yes if the statement is true. Otherwise, select No.
      NOTE: Each correct selection is worth one point.

      1. AGenerating a response to a user prompt occurs during the inference stage.
      2. BA generative AI model generates responses by copying stored documents directly from the model's training data.
      3. CA generative AI model produces output by predicting the next token based on patterns learned from the model's training data.
      Show answer & explanation

      Correct answer: Y, N, Y

      ExplanationInference generates tokens from learned patterns; models do not copy training documents verbatim for each response.

      QUESTION 16

      You need to build an AI solution that produces new product images based on written descriptions provided by users.
      Which AI workload should you use?

      1. AA. image analysis
      2. BB. image generation
      3. CC. object detection
      4. DD. optical character recognition (OCR)
      Show answer & explanation

      Correct answer: B

      ExplanationImage generation creates new visual content from text descriptions.

      QUESTION 17

      HOTSPOT -
      Select the answer that correctly completes the sentence.

        Show answer & explanation

        Correct answer: A

        ExplanationReading text from images and scanned documents uses computer vision capabilities such as OCR.

        QUESTION 18

        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?

        1. AA. Top P
        2. BB. Temperature
        3. CC. Max Completion Tokens
        4. DD. Model version settings
        Show answer & explanation

        Correct answer: C

        ExplanationMax Completion Tokens limits response length, which helps control cost and keep outputs within a defined size.

        QUESTION 19

        HOTSPOT -
        For each of the following statements, select Yes if the statement is true. Otherwise, select No.
        NOTE: Each correct selection is worth one point.

        1. AHuman-in-the-loop practices provide accountability for AI-generated decisions.
        2. BDeploying an AI system to a production environment eliminates the need for ongoing monitoring.
        3. CDisclosing the team that designed and deployed an AI system provides accountability for the system's output.
        Show answer & explanation

        Correct answer: Y, N, Y

        ExplanationAccountability includes human oversight and transparency about who built the system; production deployment still requires monitoring.

        QUESTION 20

        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?

        1. AA. Named Entity Recognition (NER)
        2. BB. key phrase extraction
        3. CC. sentiment analysis
        4. DD. summarization
        Show answer & explanation

        Correct answer: A

        ExplanationNamed Entity Recognition (NER) identifies people, organizations, locations, and other entities in text.

        Build a focused AI-901 practice routine.

        Choose AI-901 in Revizo and work through original, question-by-question practice on your iPhone. Review results, revisit what needs attention and keep your next session tied to one specific certification objective.

        Practise AI-901 with Revizo

        AI-901 practice questions.

        Is Revizo the official Microsoft exam?

        No. Revizo is an independent iPhone app for certification practice. Refer to the provider's official resources for current exam policies and registration.

        How should I use these AI-901 practice questions?

        Use the exam code to select the matching certification in Revizo, then build short, focused sessions around the areas you want to review.

        Are Revizo questions copied from live examinations?

        No. Revizo provides original practice questions for certification study. Use the provider's official objectives, documentation and policies as the source of truth for your preparation.

        What should I use alongside AI-901 practice questions?

        Use the current Microsoft objectives, documentation and registration guidance as your source of truth. Revizo is designed to support focused practice, not replace the provider's official materials.

        Where can I confirm current AI-901 requirements?

        Check the official Microsoft exam page for the latest objectives, registration details and policies.