Free Practice Questions for the Microsoft Certified: Azure AI Fundamentals AI-901 Exam (2026 Updated)

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.

The correct text analysis technique is Named Entity Recognition (NER).

Microsoft defines NER as a feature that identifies and categorizes entities in unstructured text, including people, places, and organizations.

Sentiment analysis detects positive, negative, or neutral opinion. Summarization creates shorter versions of text. Key phrase extraction identifies important phrases, but it does not specifically classify mentions as people, organizations, or locations.

Statement 1: To process prompts that contain images, you must deploy a multimodal generative AI model. = Yes

Image prompts require a vision-enabled or multimodal model. A text-only model cannot interpret image content.

Statement 2: In the Foundry playground, you can provide an image by uploading a local file or by specifying a publicly accessible URL. = Yes

The Foundry playground for vision-capable models supports adding image input to a prompt, including local uploads and image URLs.

Statement 3: A multimodal model can interpret multiple images included in a single prompt. = Yes

Vision-enabled multimodal models can accept image content items in a prompt, and multiple images can be included for the model to analyze together.

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

Azure Content Understanding in Foundry Tools uses transcription to convert speech to text from audio and video.

Transcription is the process of converting spoken audio into written text. In Azure Content Understanding, audio and video analyzers can use transcription to produce text transcripts from spoken content.

The other options are incorrect:

diarization identifies or separates speakers, such as “Speaker 1” and “Speaker 2.”

key phrase extraction identifies important phrases from text after text exists.

synthesis converts text into spoken audio, which is the opposite direction of speech-to-text.

A schema defines which fields to extract when analyzing content.

In Azure Content Understanding, the schema or fieldSchema defines the structured data that the analyzer extracts from content, including field names, types, and extraction behavior. Microsoft documentation states that Content Understanding lets you define a schema to extract, classify, or generate field values from unstructured content.

The other options are incorrect:

A keyword list does not define the complete structured output fields.

OCR-only processing extracts text, but it does not define structured fields.

A synchronous API call describes a request pattern, not the extraction schema.

The correct answer is API endpoint. After a generative AI model is deployed in Microsoft Foundry, the deployment exposes an inference endpoint through which external applications can submit requests and receive generated responses. Microsoft Foundry documentation describes deployed models as being accessible programmatically through an endpoint and associated credentials. Applications invoke the relevant REST API or SDK against this endpoint and specify the deployed model as required by the API.

An embedding vector is a numerical representation of semantic information used for similarity search, retrieval, and grounding; it is not the network interface through which a deployed model is invoked. A training dataset contains data used to train or fine-tune a model and is not called when performing inference. A URL parameter can be part of an API request, but it does not represent the deployed model ' s callable interface.

This directly aligns with the AI-901 objective to deploy a model and interact with it in the Foundry portal and to create lightweight applications that invoke deployed generative AI models through supported APIs and SDKs.

Azure Vision in Foundry Tools supports OCR capabilities for reading printed and handwritten text from images and documents. Microsoft documentation states that OCR extracts text from images and documents, including handwritten text.

Therefore, extracting data from handwritten letters is the action that can be performed by using Azure Vision in Foundry Tools.

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.

To minimize cost and keep generated responses within a defined length, configure Max Completion Tokens.

Microsoft’s Azure OpenAI / Foundry API reference defines max_completion_tokens as an upper bound for the number of tokens that can be generated for a completion. Because generated tokens contribute to usage and response length, limiting completion tokens helps control both output length and cost.

Temperature and Top P control randomness or sampling behavior, not maximum response length. Model version settings do not directly define the generated response length.

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.

Named Entity Recognition (NER) is used to extract dates, quantities, and locations from text.

Named Entity Recognition identifies and categorizes entities in text, such as people, organizations, locations, dates, times, quantities, currencies, and other structured information.

The other options are incorrect:

Key phrase extraction identifies important phrases or main topics.

Language detection identifies the language of the text.

Sentiment Analysis identifies positive, negative, neutral, or mixed sentiment.

The described solution coordinates a multi-step workflow: gathering user preferences, searching for options, requesting approval, booking services, and maintaining context across steps. This is an example of Agentic AI.

Agentic AI systems use AI agents to reason over user goals, maintain context, decide which actions to take, and use tools or services to complete tasks across multiple steps.

Why the other options are incorrect:

A. information extraction extracts structured data from content.

C. computer vision analyzes images or video.

D. generative AI creates new content, but the scenario specifically describes an autonomous, context-aware workflow with actions, which is Agentic AI.

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.

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.

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.

“AI systems must be understandable” is an example of the Microsoft responsible AI principle of transparency. Microsoft’s responsible AI framework includes fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability.

The other options are incorrect: AI systems should not merely protect company interests, should not be limited only to public data, and must not keep personal details public.

The correct answer is endpoint of the model. After a vision-enabled GPT model is deployed in Microsoft Foundry, the deployment exposes an inference endpoint that applications can call programmatically. The application sends requests containing text and, when required, image content to the deployed model through the appropriate chat-completions API endpoint. Microsoft’s documentation explicitly states that to use vision-enabled models, you call the Chat Completion API against a supported model that has been deployed.

The Foundry playground is primarily an interactive environment for testing prompts, model behavior, and multimodal inputs during development. It is not the production interface that an external application uses to submit inference requests. An evaluation pipeline is used to assess model or application quality against defined metrics and datasets, while a training dataset is associated with model training or fine-tuning rather than serving inference traffic.

Microsoft Foundry provides the endpoint and required authentication information after deployment. Applications then invoke that endpoint using an SDK or REST API, passing text and image inputs as part of the request payload.

When content is submitted to Azure Content Understanding in Foundry Tools, the analysis is asynchronous. This means the service does not return results immediately within the same HTTP request. Instead, it uses the standard Azure long-running operation (LRO) pattern — you call begin_analyze() to submit the content, which immediately returns a poller object, and then call poller.result() to wait for processing to complete and retrieve the structured extraction results.

Why the other options are wrong:

Synchronous is incorrect — the analysis pipeline involves multiple AI steps (OCR, speech transcription, schema mapping) that take time; a blocking synchronous call is not supported.

Returned only as unstructured plain text is incorrect — Azure Content Understanding returns richly structured JSON output with named fields mapped to your defined schema, not plain unstructured text.

Limited to OCR-only processing is incorrect — Content Understanding goes far beyond OCR; it supports document, audio, image, and video analyzers, and performs semantic field extraction using AI, not just character recognition.

This asynchronous design is consistent across all Azure AI services that perform complex, multi-step content processing.

The REST API request contains an image-generation style payload:

{

" prompt " : " A polar bear on the beach holding an icecream " ,

" size " : " 1024x1024 " ,

" n " : 1,

" style " : " vivid "

}

This request asks the model to generate an image from a text prompt. In Azure OpenAI, DALL-E models are used for image generation from natural language prompts.

Why the other options are incorrect:

B. Codex is associated with code generation tasks.

C. GPT-4.1 is primarily used for text/chat and multimodal reasoning, not this classic image-generation API payload.

D. Whisper is used for speech-to-text transcription.

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.

Speech

The correct answer is speech . The scenario specifically describes converting spoken customer requests into written text , which is a speech-to-text , or speech recognition, capability. Microsoft classifies speech as one of the common AI workloads in the current Azure AI Fundamentals study guide. The guide explicitly requires candidates to identify scenarios involving speech and to understand the capabilities of speech recognition and speech synthesis .

Microsoft Azure Speech in Foundry Tools provides speech-to-text functionality that converts audio streams into textual transcriptions. It supports real-time transcription, fast transcription, and batch transcription depending on the workload.

Key phrase extraction analyzes existing text to identify important words or concepts; it does not perform audio transcription. Text analysis covers operations such as sentiment analysis, entity recognition, summarization, and key phrase extraction after text already exists. Natural Language Understanding (NLU) interprets the meaning or intent of language, but the conversion from audio into written words itself is specifically a speech recognition workload .

Study Guide Reference: Identify AI concepts and capabilities → Identify AI workloads → Identify features and capabilities of speech recognition and speech synthesis.

client = OpenAI(

api_key= " ... " ,

base_url= " https://resource1.openai.azure.com/openai/v1/ " ,

)

response = client.responses.create(

model= " my-mini-gpt " ,

)

For Azure OpenAI in Microsoft Foundry, the base_url uses the Azure OpenAI resource name in the endpoint format:

https:// < resource-name > .openai.azure.com/openai/v1/

In the question, the Azure OpenAI resource is named Resource1, so the first blank must be resource1. Microsoft documentation for Azure OpenAI v1 endpoints confirms that the endpoint must use the ...openai.azure.com/openai/v1/ path.

For the model parameter, Azure OpenAI requires the deployment name, not the underlying model name. Microsoft states that Azure OpenAI always requires the deployment name when calling APIs, even when the parameter is named model.

The deployed model is gpt-4.1-mini, but the deployment name is my-mini-gpt. Therefore, the second blank must be:

model= " my-mini-gpt "

So the correct selections are:

base_url blank = resource1

model blank = my-mini-gpt

images.generate

The canonical Python call is:

response = client.images.generate(

model= " gpt-image-1 " ,

prompt=prompt

)

The correct selection is images.generate . Microsoft’s current Foundry documentation shows that image generation with a deployed GPT Image model uses the OpenAI Python SDK ' s Images API , specifically client.images.generate(). Microsoft provides an example using model= " gpt-image-1 " together with a text prompt, which directly corresponds to this scenario.

chat.completions.create is intended for chat-completion interactions rather than the standalone Images API. images.create is not the documented Python SDK method for generating an image. responses.create belongs to the Responses API , which can also orchestrate image generation through an image-generation tool, but that is a different API pattern from the explicitly requested OpenAI Images API . Microsoft distinguishes the standalone image-generation API from image generation performed through the Responses API.

One important detail in the supplied exhibit is that it visually shows client.responses. before the dropdown. Taken literally, client.responses.images.generate() would not be the documented syntax. For this question, the intended answer is clearly images.generate , yielding the documented form client.images.generate(...) .

Study Guide Reference: Microsoft Azure AI Fundamentals → Implement AI solutions by using Microsoft Foundry → Generative AI and image-generation models.

When using the Azure OpenAI Responses API with a vision-enabled model, the image must be included as an input image content item. The correct content item type is:

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

Microsoft’s Azure OpenAI Responses API documentation states that the Responses API supports image inputs, and multimodal requests use structured input content items for the request.

Why the other options are incorrect:

A. image_base64 = Incorrect. Base64 data can be used as the image data format, but the content item type is still input_image.

B. image_generation = Incorrect. This is related to generating images, not providing an image for analysis.

C. output_image = Incorrect. This would refer to generated output, not image input.

D. input_image = Correct.

Generating marketing email drafts from a short product description and target audience is a content generation task. This is a generative AI workload because the system creates new text based on the user’s prompt.

B. computer vision is for interpreting images or video.

C. text classification categorizes existing text, but does not draft new marketing emails.

D. speech recognition converts spoken audio into text.

Therefore, the correct answer is A. generative AI.

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.

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.

The correct answer is Creating captions for a video recording. Speech recognition, also called speech-to-text, converts spoken audio into textual output. Microsoft explicitly defines Azure Speech-to-Text as speech recognition technology that transcribes audio streams or prerecorded audio into text.

Caption generation is a direct application of this capability. Microsoft describes captioning as converting the audio content of a video, film, webcast, or other production into text and displaying that text visually. Therefore, creating captions from the spoken content of a video is a canonical speech-recognition workload.

Creating an audio commentary is instead associated with speech synthesis or text-to-speech because the required output is spoken audio. Identifying key phrases in a video transcript is a text-analysis/NLP task performed after the speech has already been transcribed. A voice- activated security system may involve voice authentication, speaker recognition, or command recognition, but it is not as unambiguously a speech-to-text workload as caption generation.

The AI-901 Study Guide specifically requires candidates to distinguish the features and capabilities of speech recognition and speech synthesis.

For vision-enabled Azure OpenAI / Microsoft Foundry model requests, image input can be provided by using an image URL or base64-encoded image data. Microsoft’s Azure OpenAI REST API reference states that the image content part URL field can contain either a URL of the image or the base64 encoded image data. It also states that the Responses API input_image.image_url value can be a fully qualified URL or a base64 encoded image in a data URL.

Azure Text Analytics client library

Comprehensive and Detailed Explanation with all Azure AI documents: =

The completed sentence is:

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

Azure AI Language text analysis features, such as sentiment analysis, named entity recognition, key phrase extraction, language detection, and text summarization, are accessed in code 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 workflows, not specifically Azure Language text analysis.

Azure OpenAI client library is used to call OpenAI model deployments, not Azure Language text analytics APIs.

Azure Speech SDK is used for speech-to-text and text-to-speech workloads, not text analysis.