How many Select Two (Multi-Select) Questions questions are on this page?

This page has 9 Select Two (Multi-Select) Questions scenario questions for the AI-900 exam, each with detailed explanations and wrong-answer analysis.

How should I approach AI-900 scenario questions?

Read the full scenario before looking at the answer options. Identify the constraint or requirement in the scenario, then eliminate options that are generally true but wrong for this specific case. Scenario questions reward careful reading over pattern matching.

← Back to Microsoft Azure AI Fundamentals AI-900 questions

Scenario-based practice

Select Two (Multi-Select) Questions

Practise Microsoft Azure AI Fundamentals AI-900 practice questions — original exam-style scenarios covering every exam domain, with detailed explanations, wrong-answer analysis, and common exam traps.

Start full practice test Read exam guide

scenario questions

AI-900

exam code

Microsoft

vendor

Scenario guide

How to approach select two (multi-select) questions

Multi-select questions tell you to 'Choose TWO' or 'Choose THREE'. Getting partial credit is not a thing — you must select all correct answers with no incorrect ones. The stem always states how many to choose, so trust it. These questions require precision, not best-guess elimination.

Quick answer

Select Two (Multi-Select) Questions questions test whether you can apply the concept in context, not just recognise a definition.

How the topic appears in realistic exam-style scenarios.

Which detail in the question changes the correct answer.

How to eliminate plausible but wrong options.

How to connect the question back to the wider exam objective.

Practice scenarios

Question 1mediummulti select

Full question →

A company needs to extract text from scanned invoices and receipts. Which Azure services are suitable for this task? (Select all that apply.)

A
Computer Vision
Computer Vision includes an OCR capability that can detect and extract text from images and documents.
B
Form Recognizer
Form Recognizer is designed to extract text and structured data from forms, invoices, and receipts using prebuilt models.
C
Text Analytics
Why wrong: Text Analytics is a natural language processing service that analyzes text but does not perform optical character recognition (OCR).
D
Custom Vision
Why wrong: Custom Vision is used for training custom image classification and object detection models, not for text extraction.

Full breakdown with real-world context →

Question 2mediummulti select

Full question →

A company needs to extract text from scanned invoices and receipts. Which Azure services are suitable for this task? (Choose two.)

A
Computer Vision
Computer Vision includes an OCR capability that can detect and extract text from images and documents.
B
Azure AI Document Intelligence
Azure AI Document Intelligence is designed to extract text and structured data from forms, invoices, and receipts using prebuilt models.
C
Azure AI Language
Why wrong: Azure AI Language is a natural language processing service that analyzes text but does not perform optical character recognition (OCR).
D
Custom Vision
Why wrong: Custom Vision is used for training custom image classification and object detection models, not for text extraction.

Full breakdown with real-world context →

Question 3mediummulti select

Full question →

A customer service team wants to analyze chat transcripts to understand customer sentiment and identify the most frequently discussed topics. Which two Azure AI Language features should they combine to achieve this?

A
Sentiment analysis and key phrase extraction
Sentiment analysis provides the emotional tone, and key phrase extraction pulls out the main subjects mentioned, together giving a complete picture of customer feedback.
B
Language detection and entity extraction
Language detection identifies the language but does not measure sentiment. Entity extraction identifies specific named items (e.g., product names), not general topics or sentiment.
C
Text summarization and question answering
Why wrong: Summarization condenses text, and question answering extracts answers to specific queries. Neither directly provides sentiment analysis or topic identification.
D
Named entity recognition and translation
Why wrong: NER finds entities like dates and organizations; translation converts language. Neither addresses sentiment or topic discovery.

Full breakdown with real-world context →

Question 4mediummulti select

Full question →

A customer support team wants to automatically analyze incoming emails to (1) determine the overall emotional tone (e.g., frustrated, satisfied) and (2) identify specific key phrases that indicate the reason for contact (e.g., 'return item', 'refund policy'). Which two Azure AI Language features should they use? (Choose two.)

A
Sentiment analysis
Correct: Determines the emotional tone of the text.
B
Key phrase extraction
Correct: Extracts important key phrases that indicate the reason for contact.
C
Entity recognition
Why wrong: Incorrect: Extracts predefined named entities (e.g., person, location), not general key phrases or emotional tone.
D
Language detection
Why wrong: Incorrect: Identifies the language of the text, not emotional tone or key phrases.

Full breakdown with real-world context →

Question 5mediummulti select

Full question →

A law firm needs to automatically process incoming legal documents. They have two specific requirements: (1) extract the names of all parties involved, the court name, and the filing date; (2) categorize each document as a 'complaint', 'motion', or 'subpoena'. Which two Azure AI Language features should they use? (Choose two.)

A
Sentiment analysis
Why wrong: Sentiment analysis determines the emotional tone of text, not entity extraction or document categorization.
B
Key phrase extraction
Why wrong: Key phrase extraction identifies important phrases but does not extract specific structured entities or classify documents into custom categories.
C
Custom text classification
Custom text classification can be trained to assign user-defined labels such as 'complaint', 'motion', or 'subpoena' to documents.
D
Named entity recognition (NER)
NER extracts specific entities like names of parties, court names, and dates from unstructured text, fulfilling the extraction requirement.

Full breakdown with real-world context →

Question 6mediummulti select

Full question →

A manufacturing company wants to use Azure Computer Vision to automatically inspect products on an assembly line for defects. They need to identify and locate specific types of defects (e.g., scratch, dent, crack) in product images. Which Azure Computer Vision capabilities could be used together to achieve this? (Select two options.)

A
Object Detection
Object Detection identifies and locates multiple objects (defects) in an image with bounding boxes.
B
Semantic Segmentation
Semantic Segmentation classifies each pixel, allowing detailed mapping of defect regions like scratches or dents.
C
Optical Character Recognition (OCR)
Why wrong: OCR extracts text from images, not relevant for defect detection.
D
Image Classification
Why wrong: Image Classification assigns a single label to an entire image, which cannot locate multiple defect types.

Full breakdown with real-world context →

Question 7mediummulti select

Full question →

A hotel chain wants to analyze thousands of guest reviews to understand the overall tone of feedback (positive or negative) and to extract the most commonly mentioned features (e.g., 'room cleanliness', 'staff friendliness', 'breakfast'). Which two Azure AI Language features should they combine?

A
Sentiment analysis and key phrase extraction
Sentiment analysis gives overall tone, and key phrase extraction pulls out frequent terms like 'staff friendliness', together answering both needs.
B
Entity recognition and language detection
Why wrong: Entity recognition extracts named entities (e.g., hotel names), not general features; language detection only tells the language, not sentiment or topics.
C
Key phrase extraction and entity linking
Entity linking disambiguates entities to knowledge bases, but does not provide sentiment analysis.
D
Text summarization and sentiment analysis
Why wrong: Summarization produces a condensed version, but does not extract specific key phrases or features; sentiment analysis alone does not give the list of features.

Full breakdown with real-world context →

Question 8mediummulti select

Full question →

A customer support team receives emails in multiple languages. They want to automatically determine the language of each email and then extract key phrases to summarize the issue. Which two Azure AI Language features should they use in sequence?

A
Sentiment analysis and key phrase extraction
Why wrong: Sentiment analysis assesses positive/negative emotion but does not identify the language. Key phrase extraction alone cannot determine the language.
B
Language detection and entity extraction
Language detection identifies the language, but entity extraction is for specific entities like names, not for summarizing the issue with key phrases.
C
Language detection and key phrase extraction
Language detection first identifies the language, then key phrase extraction identifies the main points in the email, which together allow routing and summary generation.
D
Entity extraction and sentiment analysis
Why wrong: Neither of these identifies the language, and entity extraction does not summarize the issue; it extracts specific predefined entities.

Full breakdown with real-world context →

Question 9mediummulti select

Full question →

A language teacher uses Azure AI Language to automatically analyze hundreds of student essays. The teacher wants to identify the main topics discussed in each essay and also understand the overall sentiment (positive, negative, or neutral) expressed. Which two prebuilt Azure AI Language features should the teacher use together to accomplish this goal?

A
Key phrase extraction and Sentiment analysis
Key phrase extraction identifies the main topics, and sentiment analysis determines the overall sentiment. This combination directly meets the teacher's requirements.
B
Entity recognition and Language detection
Why wrong: Entity recognition identifies named entities (people, places, etc.) which is not the same as identifying main topics. Language detection only identifies the language of the text, which is not needed here.
C
Text summarization and Key phrase extraction
Why wrong: Text summarization produces a condensed version of the essay, not the sentiment. The teacher also needs sentiment analysis, which is missing here.
D
Sentiment analysis and Entity recognition
Entity recognition identifies specific entities, not the main topics. The teacher also needs key phrase extraction to identify topics, which is missing here.

Full breakdown with real-world context →

These AI-900 practice questions are part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style AI-900 questions with detailed explanations, topic-based practice, mock exams, readiness tracking, and study analytics.

Select Two (Multi-Select) Questions

How to approach select two (multi-select) questions

Quick answer

Related AI-900 topic practice pages

Describe Artificial Intelligence workloads and considerations practice questions

Describe fundamental principles of machine learning on Azure practice questions

Describe features of computer vision workloads on Azure practice questions

Describe features of Natural Language Processing workloads on Azure practice questions

Describe features of generative AI workloads on Azure practice questions

AI-900 fundamentals practice questions

AI-900 scenario practice questions

AI-900 troubleshooting practice questions

Practice scenarios

A company needs to extract text from scanned invoices and receipts. Which Azure services are suitable for this task? (Select all that apply.)

A company needs to extract text from scanned invoices and receipts. Which Azure services are suitable for this task? (Choose two.)

A customer service team wants to analyze chat transcripts to understand customer sentiment and identify the most frequently discussed topics. Which two Azure AI Language features should they combine to achieve this?

A hotel chain wants to analyze thousands of guest reviews to understand the overall tone of feedback (positive or negative) and to extract the most commonly mentioned features (e.g., 'room cleanliness', 'staff friendliness', 'breakfast'). Which two Azure AI Language features should they combine?

A customer support team receives emails in multiple languages. They want to automatically determine the language of each email and then extract key phrases to summarize the issue. Which two Azure AI Language features should they use in sequence?