Microsoft AI-901 Microsoft Azure AI Fundamentals (Updated Version) Exam Practice Test

When using the OpenAI Responses API and a vision-enabled model, you can include an image in a request by providing the image as a base64-encoded image data .

Azure OpenAI / Microsoft Foundry vision requests support image input as an input_image item. The image can be provided by URL or as base64-encoded image data in the request. Microsoft documentation for Azure OpenAI batch examples also lists Base64 encoded image and Image URL as supported input patterns for Responses API requests.

The other options are incorrect:

a CSV file attachment is not an image input format for vision analysis.

an MP4 video stream is video content, not an image format.

a shared access signature (SAS) token is only an access token for a protected resource; it is not the image data itself.

The requirement is to produce new product images based on written descriptions . This is an image generation workload, because the AI system is creating entirely new images from natural language prompts.

Why the other options are incorrect:

B. image analysis is used to examine and interpret existing images.

C. object detection is used to identify and locate objects within an existing image.

D. optical character recognition (OCR) is used to extract text from images or scanned documents.

Since the solution must generate new visual content from user-provided descriptions, the correct answer is:

A. image generation

Statement 1: Voice Live returns only transcribed text. = No

Voice Live is not limited to transcription. Microsoft documentation states that the Voice Live API supports real-time bidirectional voice applications, including speech recognition, text-to-speech synthesis, avatar streaming, animation data, and audio processing.

Statement 2: Voice Live requires you to separately implement speech to text and text to speech services. = No

Voice Live provides a single real-time voice API experience rather than requiring separate STT and TTS implementations for the conversational loop. Microsoft describes live AI voice conversations as combining speech capabilities for real-time interaction, and the Voice Live API includes speech recognition and text-to-speech synthesis features.

Statement 3: Voice Live combines speech to text, reasoning, and text to speech into a single conversational experience. = Yes

This is correct. Microsoft’s guidance explains that Azure OpenAI audio/realtime capabilities are for scenarios that combine audio with language understanding, reasoning, or generation in a single model call, and Voice Live supports real-time voice-enabled applications over WebSocket connections.

GPT and DALL-E are examples of generative AI model types/families.

GPT models generate natural language text, such as answers, summaries, emails, and conversations.

DALL-E models generate images from text descriptions.

Why the other options are incorrect:

A. transformer is a model architecture, not the best answer here as a generative model type/family.

B. computer vision is an AI workload area.

E. natural language processing is an AI workload area, not a specific generative AI model type.

For a vision-enabled model, Microsoft documentation shows that multimodal prompts can include both text and image content in the same user message content array. Azure OpenAI vision models accept multimodal image-and-text input and return natural language responses.

The correct request structure is a user message with a content array containing both items, for example:

{

" role " : " user " ,

" content " : [

{ " type " : " input_text " , " text " : " What is in this image? " },

{ " type " : " input_image " , " image_url " : image_url}

]

}

This avoids sending separate requests and is therefore the best choice for quickest response time.

A and C are incorrect because they send the text and image separately.

B is incorrect because the image/question should be sent as a user message, while system messages are used for instructions and behavior.

To develop an application that analyzes text by using Azure Language in Foundry Tools, use the Azure Text Analytics client library package.

Azure Language text analysis workloads include capabilities such as sentiment analysis, key phrase extraction, named entity recognition, language detection, and other text analytics features. In application code, these text analysis capabilities are accessed by using the Azure Text Analytics client library .

The other options are incorrect:

Azure AI Projects client library is used for Foundry project and agent-related development.

Azure OpenAI client library is used to call Azure OpenAI model deployments.

Azure Speech SDK is used for speech recognition, speech synthesis, and other speech workloads.

Azure Content Understanding analysis operations are asynchronous long-running operations. Microsoft’s Python SDK documentation states that analysis starts with a begin operation, then the application polls for results until analysis completes.

Therefore, after submitting the PDF for analysis, the application should poll the operation results until the asynchronous analysis job succeeds .

Statement 1: An AI generative model is retrained before performing each user request. = No

A generative AI model is not retrained for every user request. During normal use, the model performs inference: it receives input, processes the prompt, and generates a response based on the deployed model.

Statement 2: An AI agent responds by copying and pasting answers stored in a database. = No

An AI agent does not simply copy and paste stored answers. Agents use generative AI models, instructions, context, and optionally tools or connected data sources to reason over user input and produce responses or actions.

Statement 3: An AI agent uses a generative AI model to establish actions based on user input. = Yes

This is correct. An AI agent uses a generative AI model together with instructions and available tools to interpret user input, determine the next action, and generate a response.

Verifying that machine learning models do not show racial or gender bias is an example of the Microsoft responsible AI principle of fairness .

Fairness means AI systems should treat people equitably and avoid unfair bias across demographic groups such as race, gender, age, or other protected characteristics.

Why the other options are incorrect:

A. Safety focuses on avoiding harm and operating safely.

B. Privacy and security focuses on protecting data and access.

C. Reliability focuses on consistent and dependable operation.

D. Fairness directly addresses bias and equitable treatment.

Statement 1: Azure Content Understanding in Foundry Tools can analyze only PDF documents. = No

Azure Content Understanding is not limited to PDF documents. It can analyze multiple content types, including documents, forms, images, audio, and video.

Statement 2: Azure Content Understanding in Foundry Tools results are returned in the JSON format. = Yes

Azure Content Understanding returns structured analysis results in JSON format. This is how extracted fields, values, confidence scores, and other analysis results are represented.

Statement 3: Azure Content Understanding in Foundry Tools can extract structured fields from documents and forms. = Yes

Azure Content Understanding can use analyzers and schemas to extract structured fields from documents and forms, such as invoices, receipts, contracts, and other business documents.

Requiring human reviewers to oversee AI-generated hiring recommendations and remain responsible for the final hiring decisions is an example of the Microsoft responsible AI principle of accountability .

Accountability means people and organizations remain responsible for AI systems, their decisions, and their effects. In this scenario, the AI system assists with recommendations, but humans retain oversight and responsibility for the final decision.

No

Yes

No

Comprehensive and Detailed Explanation with all Azure AI documents : =

Statement 1: Speech synthesis converts spoken audio into written text. = No

Speech synthesis, also called text to speech , converts written text into spoken audio. Converting spoken audio into written text is speech recognition or speech to text .

Statement 2: Speech recognition can detect and transcribe spoken input. = Yes

Speech recognition is used to identify spoken language in audio and convert it into text.

Statement 3: Text to speech in Azure Speech in Foundry Tools can translate text input into audible speech in a different language. = No

Text to speech converts text into spoken audio. Translation into another language is a separate translation capability, not standard text-to-speech synthesis.

The output identifies text values and labels them with entity categories, such as:

now [DateTime]

students [PersonType]

Microsoft [Organization]

175 [Quantity-Number]

Today [DateTime-Date]

This is entity recognition , also known as Named Entity Recognition (NER) . NER identifies and categorizes entities in unstructured text, such as people, organizations, locations, dates, quantities, numbers, and other named or structured values.

Why the other options are incorrect:

B. translation would convert text from one language to another.

C. key phrase extraction would return important phrases or main topics, not categorized entity labels.

D. sentiment analysis would return sentiment such as positive, negative, neutral, or mixed.

Azure Content Understanding analysis operations are long-running operations in the Python SDK. Microsoft’s Python SDK documentation states that analysis operations return a poller, and the SDK provides LROPoller types that handle polling automatically when you call .result() .

Therefore, the correct workflow is to submit the PDF by calling begin_analyze() , receive a poller, and then call:

result = poller.result()

Option B is incorrect because extraction results are not read from request headers.

Option C is incorrect because the requirement is to use Azure Content Understanding extraction, not build a manual OCR-only mapping pipeline.

Option D is incorrect because the SDK analysis pattern is asynchronous/long-running, not a simple synchronous analyze() call that returns all extracted fields in the same request.

A multimodal model can receive a single user prompt that includes the image plus instructions. The prompt can ask for both outputs in one request, for example: “Analyze this image and provide a written summary and an audio summary.” Therefore, the minimum number of user prompts is 1 .

To create an AI agent that follows a specific role and behavior, you configure system instructions . Microsoft Foundry Agent Service documentation states that agent instructions define goals, constraints, and behavior .

Option A. tokens per minute (TPM) controls throughput quota, not behavior.

Option C. temperature controls response randomness/creativity, not the agent’s role.

Option D. max completion tokens controls response length, not the agent’s role or behavioral rules.

Therefore, the correct answer is B. system instructions .

To use Azure Content Understanding in Foundry Tools, Microsoft lists a Microsoft Foundry resource as a prerequisite. The documentation states that you need a Microsoft Foundry resource created in a supported region, and that the portal lists this resource under Foundry > Foundry .

The invoice scenario is also directly aligned with Content Understanding’s intelligent document processing use case: Microsoft states that Content Understanding converts unstructured documents into structured data and gives invoice processing as an example.

Therefore, to extract structured data from invoices by using Azure Content Understanding in Foundry Tools, you should provision a Microsoft Foundry resource .

Evaluating model outcomes across demographic groups to reduce bias is an example of the Microsoft responsible AI principle of fairness .

The Microsoft responsible AI principle of fairness means AI systems should treat all people fairly and avoid unfair bias or discrimination across groups.

The other options are incorrect:

accountability means people and organizations remain responsible for AI systems and their effects.

privacy and security focuses on protecting data and controlling access.

transparency means users should understand when and how AI is being used, including system capabilities and limitations.

The completed sentence is:

An AI workload that produces new content based on user input is an example of generative AI .

Generative AI is used to create new content, such as text, images, code, audio, or other outputs, from user prompts or instructions.

The other options are incorrect:

content understanding extracts or interprets information from existing content.

information extraction identifies and extracts structured data from content.

text analysis analyzes existing text for entities, sentiment, key phrases, language, or summaries.

Fairness

Privacy and security

Transparency

Reliability and safety

Comprehensive and Detailed Explanation with all Azure AI documents : =

Evaluating model outputs to ensure that decisions are NOT biased against specific demographic groups: Fairness

Microsoft’s responsible AI principle of fairness means AI systems should treat people fairly and avoid unfair bias across demographic groups.

Encrypting sensitive customer data and restricting system access to authorized personnel: Privacy and security

The privacy and security principle requires AI systems to protect personal and sensitive data and prevent unauthorized access.

Informing users when they are interacting with an AI system and explaining the system’s capabilities and limitations: Transparency

The transparency principle requires that people understand when they are interacting with AI and understand the system’s purpose, capabilities, and limitations.

Testing AI systems under different conditions to reduce unexpected failures: Reliability and safety

The reliability and safety principle means AI systems should operate reliably and safely, including through testing and validation under expected and unexpected conditions.

Ongoing monitoring, feedback, and evaluation are goals of the Reliability & Safety principle.

The Microsoft responsible AI principle of Reliability and safety focuses on ensuring that AI systems operate consistently, safely, and as intended across different conditions. This includes testing, monitoring, collecting feedback, and evaluating system performance over time.

Why the other options are incorrect:

Human oversight and control aligns more closely with accountability.

Data governance and management aligns more closely with privacy and security.

The minimization of stereotyping, demeaning, and erasing outputs aligns more closely with fairness and inclusiveness.

The Model catalog is used for comparing and deploying a wide range of models for generative AI development.

Microsoft states that the model catalog in Foundry portal is the hub for discovering and using a wide range of models to build generative AI applications. Microsoft training also states that the model catalog is used to compare models by benchmark metrics and deploy models to endpoints.

The Microsoft responsible AI principle of transparency means AI systems should be understandable. Users should know when they are interacting with AI and should be able to understand the system’s purpose, capabilities, limitations, and the basis for its decisions.

Therefore, helping users understand the decisions made by an AI system is an example of transparency .

To return important topics from unstructured text by using Azure Language SDK, use:

client.extract_key_phrases()

Microsoft states that key phrase extraction evaluates unstructured text and returns a list of key phrases or main topics. The Azure Text Analytics client library for Python includes the extract_key_phrases method for this task.

Why the other options are incorrect:

A. client.recognize_linked_entities() identifies entities and links them to a knowledge base.

B. client.recognize_entities() identifies named entities such as people, organizations, locations, dates, and quantities.

C. client.begin_extract_summary() starts an extractive summarization operation, not key phrase extraction.

The Microsoft responsible AI principle of transparency requires that AI systems be explainable to users .

Transparency means users should understand when they are interacting with AI, what the system can and cannot do, and how outputs or predictions are generated at an appropriate level.

The other options map to different responsible AI principles:

protect sensitive user data = Privacy and security

reduce bias in decisions = Fairness

require human oversight = Accountability

input=[

{

" role " : " user " ,

" content " : [

{ " type " : " input_text " , " text " : " What is in this image? Provide 3 bullet points. " },

{ " type " : " input_image " , " image_url " : image_url},

],

}

]

print(response.output_text)

For a multimodal request that sends both text and an image to an Azure OpenAI model, the input content array uses separate content item types. Text content is sent with type: " input_text " , and image content is sent with type: " input_image " . Microsoft’s Azure OpenAI Responses API documentation shows the Responses API supports multimodal inputs and uses structured input content items in the request.

The options output_text and output_image are not used inside the user input content array. In the shown code, response.output_text is used after the response is returned to print the model’s text answer.

Tokens per minute, or TPM , is a throughput allocation for a model deployment. Assigning a higher TPM allocation increases the amount of token processing capacity available to the deployment, which affects the speed and scale at which the deployment can process requests.

It does not directly make responses longer, change region availability, or automatically add citations.

Statement 1: In the Foundry playground, you can upload a local image and include text in the same message when prompting a multimodal model. = Yes

Microsoft documentation for vision-enabled chat models states that in the chat session pane, you can select the attachment button, upload an image, add a text prompt such as “Describe this image,” and then submit it.

Statement 2: When using the OpenAI Responses API and a vision-enabled model, images can be provided only as base64-encoded image data. = No

Images are not limited to base64 data. The Responses API supports image input through an image URL, and Azure OpenAI documentation also describes examples using base64 encoded image data.

Statement 3: Prompts that include images require deploying a text-only model because multimodal capabilities are handled by the application layer. = No

Image prompts require a vision-enabled multimodal model , not a text-only model. Azure OpenAI vision-capable models accept image and text inputs directly.

The system must not discriminate based on gender, race, or age. = Fairness

This requirement maps to fairness because fairness means AI systems should avoid unfair bias and treat people equitably across demographic groups.

Personal data must be visible only to approved users. = Privacy and security

This requirement maps to privacy and security because it focuses on protecting personal data and restricting access to authorized users only.

Automated decision-making processes must be recorded so that approved users can identify why a decision was made. = Transparency

This requirement maps to transparency because recording decision-making processes helps users understand and explain how or why an AI-supported decision was made.

Microsoft’s Foundry Agent Service documentation states that tool_choice provides deterministic control over tool calling:

auto means the model decides whether to call tools.

required means the model must call one or more tools .

none means the model does not call tools.

Therefore:

A. auto = Incorrect, because the model may or may not call the Azure function.

B. none = Incorrect, because this prevents tool/function calls.

C. required = Correct, because it forces the agent to call a tool.

The Azure OpenAI function-calling documentation also confirms that tool_choice= " auto " lets the model decide whether to call a function, while tool_choice= " none " forces a user-facing response without a tool call.