When training a model, why should you randomly split the rows into separate subsets?
to train the model twice to attain better accuracy
to train multiple models simultaneously to attain better performance
to test the model by using data that was not used to train the model
When training a machine learning model, it is standard practice to randomly split the dataset into training and testing subsets. The purpose of this is to evaluate how well the model generalizes to unseen data. According to the AI-900 study guide and Microsoft Learn module “Split data for training and evaluation”, this ensures that the model is trained on one portion of the data (training set) and evaluated on another (test or validation set).
The correct answer is C. to test the model by using data that was not used to train the model.
Random splitting prevents data leakage and overfitting, which occur when a model memorizes patterns from the training data instead of learning generalizable relationships. By testing on unseen data, developers can assess true performance, ensuring that predictions will be accurate on future, real-world data.
Options A and B are incorrect because:
A. Train the model twice does not improve accuracy; model accuracy depends on data quality, feature engineering, and algorithm choice.
B. Train multiple models simultaneously refers to model comparison, not the purpose of splitting data.
Thus, the correct reasoning is that random splitting provides a reliable estimate of the model’s predictive power on new data.
Which type of natural language processing (NLP) entity is used to identify a phone number?
regular expression
machine-learned
list
Pattern-any
In Natural Language Processing (NLP), entities are pieces of information extracted from text, such as names, locations, or phone numbers. According to the Microsoft Learn module “Explore natural language processing in Azure,” Azure’s Language Understanding (LUIS) supports several entity types:
Machine-learned entities – Automatically learned based on context in training data.
List entities – Used for predefined, limited sets of values (e.g., colors or product names).
Pattern.any entities – Capture flexible, unstructured phrases in user input.
Regular expression entities – Use regex patterns to match specific data formats such as phone numbers, postal codes, or dates.
A regular expression is ideal for recognizing phone numbers because phone numbers follow specific numeric or symbol-based patterns (e.g., (555)-123-4567 or +1 212 555 0199). By defining a regex pattern, the AI model can accurately extract phone numbers regardless of text context.
Which type of machine learning should you use to predict the number of gift cards that will be sold next month?
classification
regression
clustering
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Identify features of regression machine learning”, regression is the machine learning technique used when the goal is to predict a continuous numeric value based on historical data. In this question, predicting the number of gift cards that will be sold next month involves forecasting a quantity—a numeric outcome—which is the hallmark of a regression problem.
Regression models learn patterns from past data (for example, previous months’ gift card sales, seasonality, holidays, and marketing spend) and use that information to predict future sales. Common algorithms used for regression include linear regression, decision tree regression, and boosted regression trees. The output is a continuous value such as “2,450 gift cards expected next month.”
In contrast:
A. Classification is used when the output is categorical, such as predicting whether a transaction is “fraud” or “not fraud,” or whether a customer will “renew” or “cancel.” It answers questions with discrete classes rather than numeric values.
C. Clustering is an unsupervised learning technique used to group similar data points together based on their characteristics—for example, segmenting customers into behavior-based clusters. Clustering doesn’t predict future numeric outcomes.
The AI-900 curriculum explicitly explains that regression predicts numeric values, classification predicts categories, and clustering finds natural groupings in data.
Therefore, to predict the number of gift cards to be sold, the correct and verified machine learning type is Regression.
Final Answer: B. Regression
Which two tools can you use to call the Azure OpenAI service? Each correct answer presents a complete solution.
NOTE: Each correct answer is worth one point.
Azure Command-Line Interface (CLI)
Azure REST API
Azure SDK for Python
Azure SDK for JavaScript
The correct answers are B. Azure REST API and C. Azure SDK for Python.
The Azure OpenAI Service can be accessed using multiple development interfaces. According to Microsoft Learn documentation, developers can call the service via the Azure REST API, which provides direct HTTPS-based access to the model endpoints for tasks like completions, chat, embeddings, and image generation. This interface is platform-independent and supports integration with any system capable of making HTTP requests.
Additionally, Azure SDKs offer higher-level libraries for convenient integration into applications. The Azure SDK for Python and Azure SDK for JavaScript are both supported for Azure OpenAI interaction, allowing developers to authenticate with Azure credentials, send prompts, and receive model responses programmatically.
However, among the listed options, the REST API (B) and SDK for Python (C) are most explicitly referenced in the AI-900 learning modules and Microsoft documentation as standard tools to call Azure OpenAI services.
Option A (Azure CLI) is incorrect because the CLI is used primarily for provisioning and managing Azure resources, not for directly calling OpenAI model endpoints.
Therefore, based on the Azure AI-900 and OpenAI integration guidance, the correct answers are B. Azure REST API and C. Azure SDK for Python.
Match the types of computer vision workloads to the appropriate scenarios.
To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once more than once, or not at all.
NOTE: Each correct match is worth one point.
In the Microsoft Azure AI Fundamentals (AI-900) curriculum, computer vision workloads are grouped into distinct types, each serving a specific purpose. The three major workloads illustrated here are image classification, object detection, and optical character recognition (OCR). Understanding their use cases is essential for correctly mapping them to real-world scenarios.
Generate captions for images → Image classificationThe image classification workload is used to identify the main subject or context of an image and assign descriptive labels. In Microsoft Learn’s “Describe features of computer vision workloads,” image classification models are trained to recognize content (e.g., a cat, a beach, or a city). Caption generation expands on classification results by describing the image’s contents in human-readable language—based on what the model identifies as key visual features.
Extract movie title names from movie poster images → Optical character recognition (OCR)OCR is a vision workload that detects and extracts text from images. Azure AI Vision’s Read API or Document Intelligence OCR models can identify printed or handwritten text within posters, signs, or documents. In this case, the movie title text from a poster is best extracted using OCR.
Locate vehicles in images → Object detectionThe object detection workload identifies multiple objects within an image and provides their locations using bounding boxes. It’s ideal for tasks like counting cars in a parking lot or tracking objects in traffic images.
Which scenario is an example of a webchat bot?
Determine whether reviews entered on a website for a concert are positive or negative, and then add athumbs up or thumbs down emoji to the reviews.
Translate into English questions entered by customers at a kiosk so that the appropriate person can call the customers back.
Accept questions through email, and then route the email messages to the correct person based on the content of the message.
From a website interface, answer common questions about scheduled events and ticket purchases for a music festival.
According to the Microsoft Azure AI Fundamentals (AI-900) official study materials, a webchat bot is defined as a conversational AI application that interacts with users through a web-based chat interface. It simulates human conversation using text (and sometimes voice) to answer questions, assist with transactions, or provide information automatically. Microsoft Learn’s “Describe features of common AI workloads” module highlights conversational AI as a major AI workload, where bots and virtual agents are used to provide automated, intelligent responses in real time through web, mobile, or messaging platforms.
In this scenario, the chatbot on the festival website provides immediate answers about scheduled events and ticket purchases. This aligns exactly with how a webchat bot operates — interacting with users through a website, handling repetitive inquiries, and providing consistent information without human intervention. This type of solution is commonly built using Azure Bot Service integrated with Azure Cognitive Services for Language, which allows the bot to understand user intent and respond naturally.
Let’s examine the other options to reinforce why D is correct:
A describes a text analytics or sentiment analysis scenario, not a conversational bot, because it classifies text sentiment but doesn’t “chat” with a user.
B is an example of machine translation using the Translator service, not a chatbot.
C is an email classification or natural language processing task, not a webchat interaction.
The AI-900 exam objectives clearly distinguish conversational AI from other cognitive services such as translation or sentiment analysis. Conversational AI focuses on dialogue and interaction through natural language conversation channels like websites or messaging apps.
Therefore, the verified and officially aligned answer is D. From a website interface, answer common questions about scheduled events and ticket purchases for a music festival.
You need to track multiple versions of a model that was trained by using Azure Machine Learning. What should you do?
Provision an inference duster.
Explain the model.
Register the model.
Register the training data.
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module “Explore Azure Machine Learning,” registering a model is the correct way to track multiple versions of models in Azure Machine Learning.
When you train models in Azure Machine Learning, each trained version can be registered in the workspace’s Model Registry. Registration stores the model’s metadata, including version, training environment, parameters, and lineage. Each registration automatically increments the version number, enabling you to manage, deploy, and compare multiple model iterations efficiently.
The other options are incorrect:
A. Provision an inference cluster – Used for model deployment, not version tracking.
B. Explain the model – Provides interpretability but does not track versions.
D. Register the training data – Registers data assets, not models.
You have an Al-based loan approval system.
During testing, you discover that the system has a gender bias.
Which responsible Al principle does this violate?
accountability
transparency
fairness
reliability and safety
In Microsoft’s Responsible AI principles, Fairness ensures that AI systems treat all individuals and groups equitably and make unbiased decisions. The AI-900 study guide explicitly states that fairness is violated when an AI model produces outcomes that systematically favor one group over another — such as preferring a particular gender, race, or age group.
In this scenario, a loan approval system shows gender bias, meaning it approves or rejects applications differently based on gender. This directly contradicts the fairness principle, as the AI system must make decisions solely based on relevant financial attributes (e.g., credit score, income) rather than personal characteristics.
Other principles explained in the AI-900 course include:
Accountability: Ensures human oversight and responsibility.
Transparency: Ensures users understand how decisions are made.
Reliability and Safety: Ensures consistent and accurate operation.
Since gender bias undermines equitable treatment, the principle violated is Fairness.
You need to make the press releases of your company available in a range of languages.
Which service should you use?
Translator Text
Text Analytics
Speech
Language Understanding (LUIS)
The Translator Text service (part of Azure Cognitive Services) provides real-time text translation across multiple languages. According to Microsoft Learn’s AI-900 module on “Identify features of Natural Language Processing (NLP) workloads”, translation is one of the four main NLP tasks, alongside key phrase extraction, sentiment analysis, and language understanding.
In this scenario, the company wants to make press releases available in a range of languages, which requires converting text from one language to another while preserving meaning and tone. The Translator Text API supports more than 100 languages and can be integrated into web apps, chatbots, or content management systems for automatic multilingual publishing.
The other options perform different functions:
Text Analytics (B) extracts insights such as key phrases or sentiment but does not translate.
Speech (C) focuses on converting between speech and text, not text translation.
Language Understanding (LUIS) (D) identifies user intent but does not perform translation.
Therefore, to provide multilingual press releases, the appropriate service is A. Translator Text, which ensures accurate, fast, and scalable translation across global audiences.
You need to reduce the load on telephone operators by implementing a chatbot to answer simple questions with predefined answers.
Which two AI service should you use to achieve the goal? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
Text Analytics
QnA Maker
Azure Bot Service
Translator Text
To reduce operator load with a chatbot for predefined answers:
QnA Maker provides the knowledge base for answering questions automatically.
Azure Bot Service hosts and manages the chatbot interface to interact with users.Text Analytics and Translator Text are not required for basic Q & A chatbots.
You are processing photos of runners in a race.
You need to read the numbers on the runners ' shirts to identify the runners in the photos. Which type of computer vision should you use?
image classification
optical character recognition (OCR)
object detection
facial recognition
The correct answer is B. Optical Character Recognition (OCR).
Optical Character Recognition (OCR) is a feature of Azure AI Vision that converts printed or handwritten text within images into machine-readable text. In this scenario, the goal is to read runner numbers on shirts from race photos. OCR can identify and extract these numbers, allowing them to be associated with specific participants.
Option analysis:
A. Image classification: Categorizes entire images (e.g., “runner,” “crowd”), not text.
B. Optical Character Recognition (OCR) — ✅ Correct. Extracts alphanumeric text from images.
C. Object detection: Identifies and locates objects (e.g., shoes, cars) but doesn’t read text.
D. Facial recognition: Identifies individuals by matching facial features to known identities, not by reading numbers.
Therefore, to read and extract runner numbers from photos, the correct computer vision technique is Optical Character Recognition (OCR).
Select the answer that correctly completes the sentence.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Identify features of common machine learning types”, the classification technique is a type of supervised machine learning used to predict which category or class a new observation belongs to, based on patterns learned from labeled training data.
In this scenario, a banking system that predicts whether a loan will be repaid is dealing with a binary outcome—either the loan will be repaid or will not be repaid. These two possible results represent distinct classes, making this problem a classic example of binary classification. During training, the model learns from historical data containing features such as customer income, credit score, loan amount, and repayment history, along with labeled outcomes (repaid or defaulted). After training, it can classify new applications into one of these two categories.
The AI-900 curriculum distinguishes between three key supervised and unsupervised learning approaches:
Classification: Predicts discrete categories (e.g., spam/not spam, fraud/not fraud, will repay/won’t repay).
Regression: Predicts continuous numerical values (e.g., house prices, sales forecast, temperature).
Clustering: Groups data based on similarity without predefined labels (e.g., customer segmentation).
Since the banking problem focuses on predicting a categorical outcome rather than a continuous numeric value, it fits squarely into the classification domain. In Azure Machine Learning, such tasks can be performed using algorithms like Logistic Regression, Decision Trees, or Support Vector Machines (SVMs), all configured for categorical prediction.
Therefore, per Microsoft’s official AI-900 learning objectives, a banking system predicting whether a loan will be repaid represents a classification type of machine learning problem.
Match the types of machine learning to the appropriate scenarios.
To answer, drag the appropriate machine learning type from the column on the left to its scenario on the right. Each machine learning type may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Identify features of computer vision workloads on Azure”, computer vision models can perform different types of image analysis depending on the goal of the task. The main types include image classification, object detection, and semantic segmentation. Each method analyzes images at a different level of granularity.
Image Classification → Separate images of polar bears and brown bearsImage classification assigns an entire image to a specific category or label. The model analyzes the image as a whole and determines which predefined class it belongs to. For example, in this case, the model would look at the features of each image and decide whether it shows a polar bear or a brown bear. The Microsoft Learn materials define classification as “assigning an image to a specific category.”
Object Detection → Determine the location of a bear in a photoObject detection identifies where objects appear within an image by drawing bounding boxes around them. This type of model not only classifies what object is present but also provides its location. Microsoft Learn explains that object detection “detects and locates individual objects within an image.” For instance, the model can detect a bear in a forest scene and highlight its position.
Semantic Segmentation → Determine which pixels in an image are part of a bearSemantic segmentation is the most detailed form of image analysis. It classifies each pixel in an image according to the object it belongs to. In this scenario, the model identifies every pixel corresponding to the bear’s body. The AI-900 content defines this as “classifying every pixel in an image into a category.”
To summarize:
Image classification → Categorizes entire images.
Object detection → Locates and labels objects within images.
Semantic segmentation → Labels each pixel for precise object boundaries.
https://nanonets.com/blog/how-to-do-semantic-segmentation-using-deep-learning/
Which natural language processing feature can be used to identify the main talking points in customer feedback surveys?
language detection
translation
entity recognition
key phrase extraction
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Explore natural language processing (NLP) in Azure”, key phrase extraction is a core feature of the Azure AI Language Service that enables you to automatically identify the most important ideas or topics discussed in a body of text.
When analyzing customer feedback surveys, key phrase extraction helps summarize the main talking points or recurring themes by detecting significant words and phrases. For instance, if multiple customers write comments like “The checkout process is slow” or “Website speed could be improved,” the model may extract key phrases such as “checkout process” and “website speed.” This allows businesses to quickly understand the most common subjects without manually reading each response.
Let’s review the other options:
A. Language detection: Determines the language of the text (e.g., English, French, or Spanish) but does not identify main ideas.
B. Translation: Converts text from one language to another using Azure Translator; it does not summarize or extract key information.
C. Entity recognition: Identifies named entities such as people, organizations, locations, or dates. While useful for identifying specific details, it does not capture general topics or overall discussion points.
Therefore, the appropriate NLP feature for identifying main topics or themes within textual data such as survey responses is Key Phrase Extraction.
This capability is part of the Azure AI Language Service and is commonly used in sentiment analysis pipelines, customer feedback analytics, and business intelligence workflows to summarize large text datasets efficiently.
Match the Azure Al service to the appropriate generative Al capability.
To answer, drag the appropriate service from the column on the left to its capability on the right. Each service may be used once, more than once, or not at all.
NOTE: Each correct match is worth one point.
This question maps each Azure AI service to its correct capability based on the Microsoft Azure AI Fundamentals (AI-900) syllabus and Microsoft Learn documentation on Azure Cognitive Services.
Classify and label images → Azure AI VisionAzure AI Vision (formerly Computer Vision) provides capabilities to analyze visual content, detect objects, classify images, and extract information from pictures. It includes object detection, image classification, and tagging, which are core vision tasks. This service enables businesses to build solutions that understand visual input, such as identifying products, reading signs, or detecting faces in images.
Generate conversational responses → Azure OpenAI ServiceAzure OpenAI Service integrates powerful large language models such as GPT-3.5 and GPT-4, capable of generating human-like text responses, summarizations, translations, and dialogues. These models are designed for natural language generation (NLG) and conversational AI, making them ideal for chatbots, virtual agents, and intelligent assistants that produce dynamic, context-aware replies.
Convert speech to text in real time → Azure AI SpeechAzure AI Speech provides speech-to-text capabilities (speech recognition) that convert spoken language into written text instantly. It is commonly used in transcription services, voice command systems, and live captioning applications. Additionally, the Speech service supports text-to-speech (speech synthesis) and speech translation, making it versatile for voice-based AI applications.
By understanding each service’s specialization—Vision for visual data, OpenAI for generative text, and Speech for audio processing—you can correctly match the capabilities.
You build a machine learning model by using the automated machine learning user interface (UI).
You need to ensure that the model meets the Microsoft transparency principle for responsible AI.
What should you do?
Set Validation type to Auto.
Enable Explain best model.
Set Primary metric to accuracy.
Set Max concurrent iterations to 0.
Model Explain Ability.
Most businesses run on trust and being able to open the ML “black box” helps build transparency and trust. In heavily regulated industries like healthcare and banking, it is critical to comply with regulations and best practices. One key aspect of this is understanding the relationship between input variables (features) and model output. Knowing both the magnitude and direction of the impact each feature (feature importance) has on the predicted value helps better understand and explain the model. With model explain ability, we enable you to understand feature importance as part of automated ML runs.
You need to build an app that will read recipe instructions aloud to support users who have reduced vision.
Which version service should you use?
Text Analytics
Translator Text
Speech
Language Understanding (LUIS)
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Identify features of speech capabilities in Azure Cognitive Services”, the Azure Speech service provides functionality for converting text to spoken words (speech synthesis) and speech to text (speech recognition).
In this scenario, the app must read recipe instructions aloud to assist users with visual impairments. This task is achieved through speech synthesis, also known as text-to-speech (TTS). The Azure Speech service uses advanced neural network models to generate natural-sounding voices in many languages and accents, making it ideal for accessibility scenarios such as screen readers, virtual assistants, and educational tools.
Microsoft Learn defines Speech service as a unified offering that includes:
Speech-to-text (speech recognition): Converts spoken words into text.
Text-to-speech (speech synthesis): Converts written text into natural-sounding audio output.
Speech translation: Translates spoken language into another language in real time.
Speaker recognition: Identifies or verifies a person based on their voice.
The other options do not fit the requirements:
A. Text Analytics – Performs text-based natural language analysis such as sentiment, key phrase extraction, and entity recognition, but it cannot produce audio output.
B. Translator Text – Translates text between languages but does not generate speech output.
D. Language Understanding (LUIS) – Interprets user intent from text or speech for conversational bots but does not read text aloud.
Therefore, based on the AI-900 curriculum and Microsoft Learn documentation, the correct service for converting recipe text to spoken audio is the Azure Speech service.
✅ Final Answer: C. Speech
You need to reduce the load on telephone operators by implementing a Chabot to answer simple questions with predefined answers.
Which two Al services should you use to achieve the goal? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
Azure 8ol Service
Azure Machine Learning
Translator
Language Service
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module “Explore conversational AI in Microsoft Azure,” to create a chatbot that can automatically answer simple, predefined user questions, you need two main Azure AI components — one to handle the conversation interface and another to manage the knowledge and language understanding aspect.
Azure Bot Service (A)This service is used to create, manage, and deploy chatbots that interact with users through text or voice. The Bot Service provides the framework for conversation management, user interaction, and channel integration (e.g., webchat, Microsoft Teams, Skype). It serves as the backbone of conversational AI applications and supports integration with other cognitive services like the Language Service.
Language Service (D)The Azure AI Language Service (which now includes Question Answering, formerly QnA Maker) is used to build and manage the knowledge base of predefined questions and answers. This service enables the chatbot to understand user queries and return appropriate responses automatically. The QnA capability allows you to import documents, FAQs, or structured data to create a searchable database of responses for the bot.
Why the other options are incorrect:
B. Azure Machine Learning: This service is used for building, training, and deploying custom machine learning models, not for chatbot Q & A automation.
C. Translator: This service performs language translation, which is not required for answering predefined questions unless multilingual support is specifically needed.
Therefore, to implement a chatbot that can answer simple, repetitive user questions and reduce the load on human operators, you combine Azure Bot Service (for interaction) with the Language Service (for question-answering intelligence).
Which Azure Al Document Intelligence prebuilt model should you use to extract parties and jurisdictions from a legal document?
contract
layout
general document
read
Within Azure AI Document Intelligence (formerly Form Recognizer), the Contract prebuilt model is designed to extract key information from legal and business contracts, including parties, jurisdictions, dates, and terms. According to Microsoft Learn, this prebuilt model identifies structured entities such as contracting parties, effective dates, governing jurisdictions, and termination clauses.
Layout (B) extracts text, tables, and structure but does not identify semantic information such as parties or jurisdictions.
General document (C) extracts key-value pairs and entities but lacks domain-specific contract analysis.
Read (D) performs OCR (optical character recognition) to extract raw text but not contextual metadata.
Thus, when the requirement is to extract parties and jurisdictions from a legal document, the Contract model is the correct Azure AI Document Intelligence choice.
For each of the following statements, select Yes If the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Location of a damaged product → Yes
Multiple instances of the same product → Yes
Multiple types of damaged products → Yes
All three statements are Yes, because they correctly describe the capabilities of object detection, one of the major workloads in computer vision, as defined in the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn module: “Describe features of computer vision workloads on Azure.”
Object detection is an advanced computer vision technique that allows AI systems not only to classify objects within an image but also to locate them by drawing bounding boxes around each detected object. This differentiates it from simple image classification, which only identifies what objects exist in an image without specifying their locations.
Identifying the location of a damaged product – YesAccording to Microsoft Learn, object detection can return the coordinates or bounding boxes for recognized objects. Therefore, if the model is trained to detect damaged products, it can pinpoint exactly where those defects appear within an image.
Identifying multiple instances of a damaged product – YesObject detection models can detect multiple objects of the same class in one image. For instance, if an image contains several damaged products, each will be identified and marked individually. This feature supports tasks such as automated quality inspection in manufacturing, where several defective units may appear simultaneously.
Identifying multiple types of damaged products – YesObject detection can also distinguish different classes of objects. When trained on multiple labels (e.g., cracked, scratched, or broken items), the model can detect and classify each type of damage in one image.
In Microsoft’s AI-900 framework, object detection is presented as a critical part of computer vision workloads capable of locating and classifying multiple objects and categories within visual content.
What are three Microsoft guiding principles for responsible AI? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
knowledgeability
decisiveness
inclusiveness
fairness
opinionatedness
reliability and safety
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Describe features of common AI workloads and considerations”, Microsoft has defined six guiding principles for responsible AI. These principles are intended to ensure that AI systems are developed and deployed in ways that are ethical, transparent, and beneficial to all. The six principles are: Fairness, Reliability and Safety, Privacy and Security, Inclusiveness, Transparency, and Accountability.
Let’s break down the three correct options:
Fairness – Microsoft emphasizes that AI systems should treat all individuals fairly and avoid discrimination against people based on gender, race, age, or other characteristics. Fairness ensures that outcomes and decisions from AI systems are equitable across diverse user groups. In the AI-900 learning materials, fairness is explained as a foundational value that ensures algorithms and models do not introduce or amplify societal bias.
Reliability and Safety – This principle ensures that AI systems function as intended under all expected conditions and that they can handle unexpected inputs safely. Microsoft states that AI should be tested rigorously and validated for reliability before deployment. AI systems must perform consistently and avoid causing harm due to errors or failures.
Inclusiveness – Inclusiveness focuses on empowering everyone and engaging people of all backgrounds. Microsoft’s responsible AI guidance stresses designing AI systems that understand and respect cultural, linguistic, and ability differences to make technology accessible and beneficial to all users.
Options A (knowledgeability), B (decisiveness), and E (opinionatedness) are not part of Microsoft’s Responsible AI principles. These terms do not appear in any Microsoft Learn AI-900 curriculum or official responsible AI documentation.
Thus, based on the verified AI-900 study content and Microsoft’s Responsible AI framework, the correct answer is C. Inclusiveness, D. Fairness, and F. Reliability and Safety.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
This question evaluates understanding of fundamental machine learning concepts as covered in the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Explore the machine learning process.” These statements relate to data labeling, model evaluation practices, and performance metrics—three essential parts of building and assessing a machine learning model.
Labelling is the process of tagging training data with known values → YesAccording to Microsoft Learn, “Labeling is the process of tagging data with the correct output value so the model can learn relationships between inputs and outputs.” This is essential for supervised learning, where models require historical data with known outcomes. For example, if training a model to recognize fruit images, each image is labeled as “apple,” “banana,” or “orange.” Hence, this statement is true.
You should evaluate a model by using the same data used to train the model → NoThe AI-900 guide stresses that using the same data for both training and evaluation can cause overfitting, where the model performs well on training data but poorly on unseen data. Instead, the dataset is split into training and testing (or validation) subsets. Evaluation must use test data that the model has never seen before to ensure an unbiased measure of performance. Therefore, this statement is false.
Accuracy is always the primary metric used to measure a model’s performance → NoMicrosoft Learn emphasizes that accuracy is only one metric and not always the best choice. Depending on the problem type, other metrics such as precision, recall, F1-score, or AUC (Area Under the Curve) may be more appropriate—especially in cases with imbalanced datasets. For example, in fraud detection, recall may be more important than accuracy. Thus, this statement is false.
You use drones to identify where weeds grow between rows of crops to send an Instruction for the removal of the weeds. This is an example of which type of computer vision?
scene segmentation
optical character recognition (OCR)
object detection
Object detection is similar to tagging, but the API returns the bounding box coordinates for each tag applied. For example, if an image contains a dog, cat and person, the Detect operation will list those objects together with their coordinates in the image.
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Identify features of Natural Language Processing (NLP) workloads and services,” the Azure Cognitive Service for Language – Question Answering capability is designed to allow applications to respond to user questions using information from a prebuilt or custom knowledge base. It relies on Natural Language Processing (NLP) to match user queries to the most relevant answers but does not directly execute queries against databases or infer user intent.
“You can use Language Service’s question answering to query an Azure SQL database.” → NOThe Question Answering feature does not connect directly to or query structured databases such as Azure SQL. Instead, it retrieves answers from unstructured or semi-structured content (FAQs, manuals, documents). Querying SQL databases would require traditional database access, not a cognitive service.
“You should use Language Service’s question answering when you want a knowledge base to provide the same answer to different users who submit similar questions.” → YESThis statement is correct and aligns exactly with Microsoft’s official documentation. Question Answering enables organizations to create a knowledge base that can automatically answer repeated or similar customer queries using natural language understanding. For instance, two users asking “How do I reset my password?” and “Can you help me change my password?” would receive the same predefined response.
“Language Service’s question answering can determine the intent of a user utterance.” → NODetermining user intent is handled by Language Understanding (LUIS) or Conversational Language Understanding, not by Question Answering. While both belong to the Language Service, Question Answering focuses on retrieving relevant answers, whereas LUIS focuses on intent detection and entity extraction.
Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents?
Azure Al Custom Vision
Azure Al Document Intelligence
Azure Al Language
Azure Al face
Accelerate your business processes by automating information extraction. Form Recognizer applies advanced machine learning to accurately extract text, key/value pairs, and tables from documents. With just a few samples, Form Recognizer tailors its understanding to your documents, both on-premises and in the cloud. Turn forms into usable data at a fraction of the time and cost, so you can focus more time acting on the information rather than compiling it.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Statements
Yes
No
A bot that responds to queries by internal users is an example of a conversational AI workload.
✅ Yes
An application that displays images relating to an entered search term is an example of a conversational AI workload.
✅ No
A web form used to submit a request to reset a password is an example of a conversational AI workload.
✅ No
According to the Microsoft Azure AI Fundamentals (AI-900) official study materials, conversational AI workloads are those that enable interaction between humans and AI systems through natural language conversation, either by text or speech. These workloads are typically implemented using Azure Bot Service, Azure Cognitive Services for Language, and Azure OpenAI Service. The key characteristic of a conversational AI workload is the presence of dialogue—the AI interprets user intent and provides a meaningful, contextual response in a conversation-like manner.
“A bot that responds to queries by internal users is an example of a conversational AI workload.” → YESThis fits the definition perfectly. A chatbot that helps employees (internal users) by answering questions about policies, IT issues, or HR procedures is a typical example of conversational AI. It uses natural language understanding to interpret questions and provide automated responses. Microsoft Learn explicitly identifies chatbots as conversational AI solutions designed for both internal and external interactions.
“An application that displays images relating to an entered search term is an example of a conversational AI workload.” → NOThis is not conversational AI because there is no dialogue or language understanding involved. It is an example of information retrieval or computer vision if it uses image recognition, but not conversation.
“A web form used to submit a request to reset a password is an example of a conversational AI workload.” → NOA password reset form is a simple UI-driven process that doesn’t require AI or conversational logic. It performs a fixed function based on user input but does not understand or respond to natural language.
Therefore, based on the AI-900 study guide, only the first statement is an example of a conversational AI workload, while the second and third statements are not.
You run a charity event that involves posting photos of people wearing sunglasses on Twitter.
You need to ensure that you only retweet photos that meet the following requirements:
Include one or more faces.
Contain at least one person wearing sunglasses.
What should you use to analyze the images?
the Verify operation in the Face service
the Detect operation in the Face service
the Describe Image operation in the Computer Vision service
the Analyze Image operation in the Computer Vision service
The scenario requires two checks on each photo: (1) there is at least one face, and (2) at least one detected face is wearing sunglasses. The Azure AI Face service – Detect operation is purpose-built for this combination. It detects faces and returns per-face attributes, including glasses type, so you can enforce both rules in a single pass. From the official guidance, the Detect API “detects human faces in an image and returns the rectangle coordinates of their locations” and exposes face attributes such as glasses. A concise attribute extract states: “Glasses: NoGlasses, ReadingGlasses, Sunglasses, Swimming Goggles.” With this, you can count faces (requirement 1) and then verify that at least one face’s glasses attribute equals sunglasses (requirement 2).
By contrast, other options don’t align as precisely:
A. Verify (Face service) compares whether two detected faces belong to the same person. It does not provide content attributes like sunglasses; it requires face inputs for identity/one-to-one scenarios, which doesn’t meet your content-filter goal.
C. Describe Image (Computer Vision) returns a natural-language caption of the whole image. While a caption might mention “a person wearing sunglasses,” it’s not guaranteed, is not face-scoped, and offers less deterministic filtering than a structured attribute on a detected face.
D. Analyze Image (Computer Vision) can return tags such as “person” or sometimes “sunglasses,” but those tags are image-level and not bound to specific faces. You need to ensure that a detected face (not just any region) is wearing sunglasses. Face-scoped attributes from Face Detect are more reliable for this logic.
Therefore, the most accurate and exam-aligned choice is B. the Detect operation in the Face service, because it allows you to programmatically confirm face presence and per-face sunglasses in a precise, rule-driven workflow.
Match the machine learning models to the appropriate deceptions.
To answer, drag the appropriate model from the column on the left to its description on the right Each model may be used once, more than once, or not at all.
NOTE: Each correct match is worth one point.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Identify features of common machine learning types”, the three main machine learning model types differ by their purpose and the kind of data they use — whether supervised (using labeled data) or unsupervised (using unlabeled data).
Regression → A supervised machine learning model used to predict numeric values.Regression is a type of supervised learning that predicts continuous numerical outcomes. It learns the relationship between input features (independent variables) and a continuous target variable (dependent variable). Examples include predicting house prices, sales revenue, or temperature. The AI-900 curriculum emphasizes regression for “predicting numeric values based on known data,” using algorithms such as linear regression or decision tree regression.
Classification → A supervised machine learning model used to predict categories.Classification is also a supervised learning technique, but it predicts discrete outcomes (classes) instead of continuous values. It assigns input data to one or more categories based on learned patterns. Typical examples include spam detection (spam vs. not spam), sentiment analysis (positive, neutral, negative), or predicting loan approval (approved/denied). The AI-900 study materials describe classification as “predicting a category or label for new observations.”
Clustering → An unsupervised machine learning model used to group similar entities based on features.Clustering is an unsupervised learning approach, meaning it works on unlabeled data. It automatically identifies patterns and groups similar data points into clusters based on shared characteristics. Examples include customer segmentation (grouping customers by behavior) and grouping similar documents. The AI-900 learning module explains clustering as “discovering natural groupings in data without predefined labels.”
Thus, per Microsoft’s official AI-900 learning objectives:
Regression → Predicts numeric/continuous values.
Classification → Predicts categories/labels.
Clustering → Groups similar entities (unsupervised).
✅ Final Verified Configuration:
Regression → Predict numeric values
Classification → Predict categories
Clustering → Group similar entities based on features
What is an example of a Microsoft responsible Al principle?
Al systems should treat people fairly.
Al systems should NOT reveal the details of their design.
Al systems should use black-box models.
Al systems should protect the interests of developers.
Full Detailed Explanation (250–300 words):
The correct answer is A. AI systems should treat people fairly.
This statement aligns with one of Microsoft’s six Responsible AI principles, which are:
Fairness – AI systems should treat all people fairly and avoid bias.
Reliability and Safety
Privacy and Security
Inclusiveness
Transparency
Accountability
The principle of Fairness ensures that AI models do not discriminate based on factors such as race, gender, age, or socioeconomic background. For example, a loan approval or hiring model must provide equal opportunity to all qualified applicants regardless of demographic differences.
B (Not revealing design details) contradicts Transparency, which promotes openness about AI functionality.
C (Black-box models) goes against Microsoft’s push for Explainable AI.
D (Protect developers’ interests) is not part of Microsoft’s Responsible AI framework.
Therefore, the verified correct answer is A. AI systems should treat people fairly.
Select the answer that correctly completes the sentence.
The correct completion of the sentence is:
“The interactive answering of questions entered by a user as part of an application is an example of natural language processing.”
According to the Microsoft Azure AI Fundamentals (AI-900) official study materials, Natural Language Processing (NLP) is a branch of Artificial Intelligence that focuses on enabling computers to understand, interpret, and respond to human language in a way that is both meaningful and useful. It is one of the key AI workloads described in the “Describe features of common AI workloads” module on Microsoft Learn.
When a user types a question into an application and the system responds interactively — such as in a chatbot, Q & A system, or virtual assistant — this process requires language understanding. NLP allows the system to process the input text, determine user intent, extract relevant entities, and generate an appropriate response. This is the foundational capability behind services such as Azure Cognitive Service for Language, Language Understanding (LUIS), and QnA Maker (now integrated as Question Answering in the Language service).
Microsoft’s study guide explains that NLP workloads include the following key scenarios:
Language understanding: Determining intent and context from text or speech.
Text analytics: Extracting meaning, key phrases, sentiment, or named entities.
Conversational AI: Powering bots and virtual agents to interact using natural language.These systems rely on NLP models to analyze user inputs and respond accordingly.
In contrast:
Anomaly detection identifies data irregularities.
Computer vision analyzes images or video.
Forecasting predicts future values based on historical data.
Therefore, based on the AI-900 official materials, the interactive answering of user questions through an application clearly falls under Natural Language Processing (NLP).
What should you use to identify similar faces in a set of images?
Azure Al Vision
Azure Al Custom Vision
Azure Al Language
Azure OpenAI Service
The correct service to identify similar faces in a set of images is Azure AI Vision, which includes the Face API capability. According to the Microsoft Learn module “Analyze images with Azure AI Vision”, this service provides prebuilt models for face detection, facial recognition, and similarity matching.
The Face API can detect individual faces in images and extract unique facial features to create a face embedding (a numerical representation of the face). It then compares these embeddings across multiple images to determine whether faces are similar or belong to the same person. This functionality is commonly used in identity verification, photo management systems, and security solutions.
The other options are incorrect:
B. Azure AI Custom Vision is used for custom image classification or object detection but does not provide face similarity or recognition features.
C. Azure AI Language processes text-based data (sentiment, entities, key phrases) — not visual content.
D. Azure OpenAI Service focuses on text generation, summarization, and conversation, not facial analysis.
Therefore, the Microsoft-verified service for identifying similar faces across images is A. Azure AI Vision.
Which feature of the Azure Al Language service should you use to automate the masking of names and phone numbers in text data?
Personally Identifiable Information (Pll) detection
entity linking
custom text classification
custom named entity recognition (NER)
The correct answer is A. Personally Identifiable Information (PII) detection.
In the Azure AI Language service, PII detection is a built-in feature designed to automatically identify and redact sensitive or confidential information from text data. According to the Microsoft Learn module “Identify capabilities of Azure AI Language” and the AI-900 study guide, this capability can detect personal data such as names, phone numbers, email addresses, credit card numbers, and other identifiers.
When applied, the service scans input text and either masks or removes these PII elements based on configurable parameters, ensuring compliance with data privacy regulations like GDPR or HIPAA.
For example, if a document contains “John Doe’s phone number is 555-123-4567,” PII detection can return “******’s phone number is ***********,” thereby preventing exposure of sensitive personal details.
Option analysis:
A. Personally Identifiable Information (PII) detection: ✅ Correct. It identifies and masks sensitive data in text.
B. Entity linking: Connects recognized entities to known data sources like Wikipedia; not used for redaction.
C. Custom text classification: Classifies text into predefined categories; not designed for masking personal data.
D. Custom named entity recognition (NER): Detects domain-specific entities you define but doesn’t automatically mask them.
Therefore, to automate masking of names and phone numbers, the appropriate Azure AI Language feature is PII detection.
You plan to use Azure Cognitive Services to develop a voice controlled personal assistant app.
Match the Azure Cognitive Services to the appropriate tasks.
To answer, drag the appropriate service from the column on the left to its description on the right Each service may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn Cognitive Services documentation, developing a voice-controlled personal assistant app involves integrating multiple Azure AI services that specialize in different aspects of language and speech processing. The three services in focus—Azure AI Speech, Azure AI Language Service, and Azure AI Translator Text—perform unique but complementary roles in conversational AI systems.
Convert a user’s speech to text → Azure AI SpeechThe Azure AI Speech service provides speech-to-text (STT) capabilities. It enables applications to recognize spoken language and convert it into written text in real time. This is often the first step in voice-enabled applications, transforming audio input into a machine-readable format that can be analyzed further.
Identify a user’s intent → Azure AI Language serviceOnce speech has been transcribed, the Azure AI Language service (which includes capabilities like Conversational Language Understanding and Text Analytics) interprets the meaning of the text. It detects the user’s intent (what the user wants to accomplish) and extracts entities (key data points) from the input. This service helps the assistant understand commands like “Book a flight” or “Set a reminder.”
Provide a spoken response to the user → Azure AI SpeechAfter determining an appropriate response, the system uses the text-to-speech (TTS) feature of Azure AI Speech to convert the assistant’s text-based reply back into natural-sounding spoken language, allowing the user to hear the response.
Together, these services form the backbone of a conversational AI system: Speech-to-Text → Language Understanding → Text-to-Speech, aligning precisely with the AI-900 curriculum’s explanation of how Azure Cognitive Services enable intelligent voice-based interactions.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
To complete the sentence, select the appropriate option in the answer area.
Classification
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Describe features of common AI workloads”, classification is a supervised machine learning technique used when the goal is to predict which category or class an item belongs to. In supervised learning, the model is trained with labeled data—data that already contains known outcomes. The system learns patterns and relationships between input features and their corresponding labels so it can predict future classifications accurately.
In the scenario provided — “A banking system that predicts whether a loan will be repaid” — the model’s output is a binary decision, meaning there are two possible outcomes:
The loan will be repaid (positive class)
The loan will not be repaid (negative class)
This kind of problem involves predicting a discrete value (a label or category), not a continuous numeric output. Therefore, it perfectly fits the classification type of machine learning.
The AI-900 learning materials describe classification as being used in many real-world examples, including:
Determining whether an email is spam or not spam.
Predicting whether a customer will churn (leave) or stay.
Detecting fraudulent transactions.
Assessing medical test results as positive or negative.
By contrast:
Regression predicts continuous numeric values, such as predicting house prices, temperatures, or sales revenue. It would not apply here because repayment prediction is not a numeric value but a categorical decision.
Clustering is an unsupervised learning method that groups similar data points without predefined categories, such as segmenting customers by purchasing behavior.
Thus, based on Microsoft’s Responsible AI and AI-900 study guide concepts, a banking system that predicts whether a loan will be repaid uses the Classification type of machine learning.
What is an example of a Microsoft responsible Al principle?
Al systems should protect the interests of developers.
Al systems should be in the public domain.
Al systems should be secure and respect privacy.
Al systems should make personal details accessible.
Microsoft’s Responsible AI principles are central to the AI-900 curriculum and consist of six key tenets:
Fairness – AI systems should treat all people fairly.
Reliability and safety – AI systems should perform reliably and safely.
Privacy and security – AI systems should be secure and respect user privacy.
Inclusiveness – AI systems should empower everyone.
Transparency – AI systems should be understandable.
Accountability – People should be accountable for AI outcomes.
The statement “AI systems should be secure and respect privacy” reflects the Privacy and Security principle, which ensures AI solutions protect personal data and operate within compliance frameworks. Microsoft’s responsible AI framework emphasizes building trust by safeguarding sensitive data used in AI applications.
The other options do not align with official responsible AI principles; for example, AI systems need not “be in the public domain,” nor are they meant to prioritize developers’ interests or expose personal details. Hence, the correct and Microsoft-verified answer is C. AI systems should be secure and respect privacy.
You need to generate cartoons for use in a brochure. Each cartoon will be based on a text description.
Which Azure OpenAI model should you use?
Codex
DALL-E
GPT-3.5
GPT-4
To generate cartoons or images from text descriptions, the correct Azure OpenAI model is DALL-E. As described in Microsoft’s OpenAI integration documentation, DALL-E is a generative image model that converts natural language prompts into images, illustrations, and artwork.
Codex is for code generation, GPT-3.5 and GPT-4 are for text and reasoning tasks, not image creation. Therefore, B. DALL-E is correct.
You use Azure Machine Learning designer to build a model pipeline. What should you create before you can run the pipeline?
a Jupyter notebook
a registered model
a compute resource
Before running a pipeline in Azure Machine Learning Designer, you must have an available compute resource (such as a compute instance or compute cluster). Compute provides the processing power required to train, evaluate, and execute the pipeline’s modules.
Other options:
A. Jupyter notebook – Used for code-first development, not required for Designer pipelines.
B. Registered model – Created after running a pipeline, not before.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
This question assesses knowledge of the Azure Cognitive Services Speech and Text Analytics capabilities, as described in the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn modules “Explore natural language processing” and “Explore speech capabilities.” These services are part of Azure Cognitive Services, which provide prebuilt AI capabilities for speech, language, and text understanding.
You can use the Speech service to transcribe a call to text → YesThe Speech-to-Text feature in the Azure Speech service automatically converts spoken words into written text. Microsoft Learn explains: “The Speech-to-Text capability enables applications to transcribe spoken audio to text in real time or from recorded files.” This makes it ideal for call transcription, voice assistants, and meeting captioning.
You can use the Text Analytics service to extract key entities from a call transcript → YesOnce a call has been transcribed into text, the Text Analytics service (part of Azure Cognitive Services for Language) can process that text to extract key entities, key phrases, and sentiment. For example, it can identify names, organizations, locations, and product mentions. Microsoft Learn notes: “Text Analytics can extract key phrases and named entities from text to derive insights and structure from unstructured data.”
You can use the Speech service to translate the audio of a call to a different language → YesThe Azure Speech service also includes Speech Translation, which can translate spoken language in real time. It converts audio input from one language into translated text or speech output in another language. Microsoft Learn describes this as: “Speech Translation combines speech recognition and translation to translate spoken audio to another language.”
You ate building a Conversational Language Understanding model for an e-commerce business.
You need to ensure that the model detects when utterances are outside the intended scope of the model.
What should you do?
Export the model.
Create a new model.
Add utterances to the None intent.
Create a prebuilt task entity.
In Conversational Language Understanding (CLU), a core service within Azure AI Language, intents represent the goals or purposes behind user utterances (for example, “Track my order” or “Cancel my subscription”). However, in real-world scenarios, users often provide inputs that do not match any defined intent. To handle such cases gracefully, Microsoft recommends including a “None” intent that captures out-of-scope utterances — text that doesn’t belong to any other intent in your model.
According to the Microsoft Learn module: “Build a Conversational Language Understanding app”, the None intent serves as a catch-all or fallback category for utterances that the model should ignore or respond to with a default message (e.g., “I’m sorry, I don’t understand that.”). By training the model with multiple examples of irrelevant or unrelated utterances in this intent, you improve its ability to distinguish between valid and invalid user inputs.
The other options are incorrect:
A. Export the model: Exporting only saves or transfers the model; it does not influence how the model detects irrelevant utterances.
B. Create a new model: A new model would not inherently solve out-of-scope detection unless properly trained with a None intent.
D. Create a prebuilt task entity: Entities identify specific data (like dates or products) within valid intents, not irrelevant utterances.
Thus, the correct approach to ensure that your CLU model can detect utterances outside its intended scope is to add examples of unrelated or off-topic phrases to the None intent. This improves classification accuracy and prevents incorrect intent matches.
✅ Correct Answer: C. Add utterances to the None intent
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Box 1: No
Box 2: Yes
Box 3: Yes
Anomaly detection encompasses many important tasks in machine learning:
Identifying transactions that are potentially fraudulent.
Learning patterns that indicate that a network intrusion has occurred.
Finding abnormal clusters of patients.
Checking values entered into a system.
In which two scenarios can you use the Azure Al Document Intelligence service (formerly Form Recognizer)? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
Extract the invoice number from an invoice.
Identify the retailer from a receipt.
Find images of products in a catalog.
Translate a form from French to English.
The Azure AI Document Intelligence service (formerly Form Recognizer) is designed to analyze, extract, and structure data from scanned or digital documents such as invoices, receipts, contracts, and forms. According to the Microsoft Learn module “Extract data from documents with Azure AI Document Intelligence”, the service uses optical character recognition (OCR) and pretrained machine learning models to automatically extract key information.
A. Extract the invoice number from an invoice – YESThe prebuilt invoice model in Document Intelligence can detect and extract key fields such as invoice number, date, total amount, tax, and vendor details from scanned or digital invoices.
B. Identify the retailer from a receipt – YESThe prebuilt receipt model can recognize fields like merchant name (retailer), transaction date, total spent, and tax amount, making this option correct as well.
C. Find images of products in a catalog – NOThis is a computer vision or Custom Vision use case, not a document data extraction task.
D. Translate a form from French to English – NOTranslation involves Azure AI Translator, part of the Language service, not Document Intelligence.
Hence, the correct and Microsoft-verified answers are:
✅ A. Extract the invoice number from an invoice
✅ B. Identify the retailer from a receipt
Select the answer that correctly completes the sentence.
“features.”
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Describe fundamental principles of machine learning on Azure,” in a machine learning model, the data used as inputs are known as features, while the data that represents the output or target prediction is known as the label.
Features are measurable attributes or properties of the data used by a model to learn patterns and make predictions. They are also referred to as independent variables because they influence the result that the model tries to predict. For example, in a machine learning model that predicts house prices:
Features might include square footage, location, and number of bedrooms, while
The label would be the house price (the value being predicted).
In the context of Azure Machine Learning, during model training, features are passed into the algorithm as input variables (X-values), and the label is the corresponding output (Y-value). The model then learns the relationship between the features and the label.
Let’s review the incorrect options:
Functions: These are mathematical operations or relationships used inside algorithms, not the input data itself.
Labels: These are the outputs or results that the model predicts, not the inputs.
Instances: These refer to individual data records or rows in the dataset, not the input fields themselves.
Hence, in any supervised or unsupervised learning process, the input data (independent variables) are called features, and the model uses them to predict labels (dependent variables).
Select the answer that correctly completes the sentence.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Describe features of natural language processing (NLP) workloads on Azure,” Natural Language Processing refers to the branch of AI that enables computers to interpret, understand, and generate human language. One of the main NLP workloads identified by Microsoft is speech-to-text conversion, which transforms spoken words into written text.
Creating a text transcript of a voice recording perfectly fits this definition because it involves converting audio language data into text form — a process handled by speech recognition models. These models analyze the acoustic features of human speech, segment phonemes, identify words, and produce a text transcript. On Azure, this function is implemented using the Azure Cognitive Services Speech-to-Text API, part of the Language and Speech services.
Let’s examine the other options to clarify why they are incorrect:
Computer vision workload: Involves interpreting and analyzing visual data such as images and videos (e.g., object detection, facial recognition). It does not deal with speech or audio.
Knowledge mining workload: Refers to extracting useful information from large amounts of structured and unstructured data using services like Azure Cognitive Search, not transcribing audio.
Anomaly detection workload: Involves identifying unusual patterns in data (e.g., fraud detection or sensor anomalies), unrelated to language or speech.
In summary, when a system creates a text transcript from spoken audio, it is performing a speech recognition task—classified under Natural Language Processing (NLP). This workload helps make spoken content searchable, analyzable, and accessible, aligning with Microsoft’s Responsible AI goal of enhancing accessibility through language understanding.
You need to build an image tagging solution for social media that tags images of your friends automatically. Which Azure Cognitive Services service should you use?
Computer Vision
Face
Text Analytics
Form Recognizer
The correct answer is B. Face because the Azure Face service, part of Azure Cognitive Services, provides capabilities for detecting, recognizing, and analyzing human faces in images. According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Explore computer vision”, the Face service can automatically detect faces, determine attributes such as age, gender, emotion, and identify or verify individuals based on facial features.
In this scenario, the goal is to build an image tagging solution that automatically tags images of friends on social media. This requires the ability to recognize and match faces of known individuals, which is a key feature of the Face API. The API uses facial recognition technology to create face IDs for detected faces and can compare new faces against stored face data to identify known individuals. Microsoft Learn notes: “The Face service can detect, recognize, and identify people in images, enabling automated tagging or authentication scenarios.”
Other options explained:
A. Computer Vision identifies objects, landmarks, and general content but does not specialize in identifying individual people.
C. Text Analytics analyzes textual data for sentiment, key phrases, or entities, not image data.
D. Form Recognizer extracts structured data from forms or receipts, unrelated to face detection.
Thus, for automatically tagging people in photos, Azure Face is the correct and most suitable service.
You deploy the Azure OpenAI service to generate images.
You need to ensure that the service provides the highest level of protection against harmful content.
What should you do?
Configure the Content filters settings.
Customize a large language model (LLM).
Configure the system prompt
Change the model used by the Azure OpenAI service.
The correct answer is A. Configure the Content filters settings.
When using the Azure OpenAI Service for text or image generation, Microsoft provides built-in content filtering to help detect and block potentially harmful or unsafe outputs. These filters are part of Microsoft’s Responsible AI framework and are designed to prevent the generation of offensive, violent, sexual, or otherwise restricted content.
To ensure the highest level of protection, you can configure content filter settings within the Azure OpenAI deployment. This allows you to define stricter policies based on your organization’s safety requirements. For image generation models such as DALL·E, enabling or strengthening these filters ensures that inappropriate or unsafe images are not generated or returned.
B (Customize an LLM): Customization affects behavior but not safety filtering.
C (Configure the system prompt): Adjusts response style but doesn’t guarantee content safety.
D (Change the model): Different models have similar filter systems; protection level depends on filter configuration, not the model itself.
Select the answer that correctly completes the sentence.
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module “Explore computer vision in Microsoft Azure,” Optical Character Recognition (OCR) is a computer vision capability that detects and extracts printed or handwritten text from images or scanned documents and converts it into machine-readable digital text.
In this scenario, a historian wants to digitize newspaper articles — which means converting physical or scanned images of printed text into digital text for easier searching, archiving, and analysis. This is exactly the function of OCR. By using OCR, the historian can take photos or scans of old newspapers and extract the words into editable digital documents, preserving valuable historical information.
OCR is a key feature of the Azure Computer Vision service, which provides capabilities such as:
Extracting text from images or PDFs.
Reading both printed and handwritten text in multiple languages.
Converting physical documents into searchable digital files.
Let’s examine the incorrect options:
Facial analysis: Detects facial features, age, gender, and emotions — unrelated to text extraction.
Image classification: Identifies what an image contains (e.g., “dog,” “car,” or “building”) but doesn’t extract text.
Object detection: Identifies and locates objects within an image using bounding boxes, not suitable for text recognition.
Therefore, to digitize newspaper articles and convert printed words into editable digital text, the correct technology to use is Optical Character Recognition (OCR), provided by the Azure Computer Vision API.
✅ Final Answer: optical character recognition (OCR)
Match the facial recognition tasks to the appropriate questions.
To answer, drag the appropriate task from the column on the left to its question on the right. Each task may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
The correct matches are based on the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module “Explore computer vision in Microsoft Azure.” These materials explain that facial recognition tasks can be categorized into four major operations: verification, identification, similarity, and grouping. Each task serves a distinct purpose in facial recognition scenarios.
Verification – “Do two images of a face belong to the same person?”The verification task determines whether two facial images represent the same individual. Azure Face API compares the facial features and returns a confidence score indicating the likelihood that the two faces belong to the same person.
Similarity – “Does this person look like other people?”The similarity task compares a face against a collection of faces to find visually similar individuals. It does not confirm identity but measures how closely two or more faces resemble each other.
Grouping – “Do all the faces belong together?”Grouping organizes a set of unknown faces into clusters based on similar facial features. This is used when identities are not known beforehand, helping discover potential duplicates or visually similar clusters within an image dataset.
Identification – “Who is this person in this group of people?”The identification task is used when the system tries to determine who a specific person is by comparing their face against a known collection (face database or gallery). It returns the identity that best matches the input face.
According to Microsoft’s AI-900 training, these tasks form the basis of Azure Face API’s capabilities. Each helps solve a different type of facial recognition problem—from matching pairs to discovering unknown identities—making them essential components of responsible AI-based vision systems.
Which OpenAI model does GitHub Copilot use to make suggestions for client-side JavaScript?
GPT-4
Codex
DALL-E
GPT-3
According to the Microsoft Azure AI Fundamentals (AI-900) learning path and Microsoft Learn documentation on GitHub Copilot, GitHub Copilot is powered by OpenAI Codex, a specialized language model derived from the GPT-3 family but fine-tuned specifically on programming languages and code data.
OpenAI Codex was designed to translate natural language prompts into executable code in multiple programming languages, including JavaScript, Python, C#, TypeScript, and Go. It can understand comments, function names, and code structure to generate relevant code suggestions in real time.
When a developer writes client-side JavaScript, GitHub Copilot uses Codex to analyze the context of the file and generate intelligent suggestions, such as completing functions, writing boilerplate code, or suggesting improvements. Codex can also explain what specific code does and provide inline documentation, which enhances developer productivity.
Option A (GPT-4): While some newer versions of GitHub Copilot (Copilot X) may integrate GPT-4 for conversational explanations, the core code completion engine remains based on Codex, as per the AI-900-level content.
Option C (DALL-E): Used for image generation, not for programming tasks.
Option D (GPT-3): Codex was fine-tuned from GPT-3 but has been further trained specifically for code generation tasks.
Therefore, the verified and official answer from Microsoft’s AI-900 curriculum is B. Codex — the OpenAI model used by GitHub Copilot to make suggestions for client-side JavaScript and other programming languages.
Which Azure Machine Learning capability should you use to quickly build and deploy a predictive model without extensive coding?
ML pipelines
Copilot
DALL-E
automated machine learning (automated ML)
According to the Microsoft Azure AI Fundamentals (AI-900) curriculum and Microsoft Learn’s “Explore Automated Machine Learning in Azure Machine Learning” module, Automated ML (AutoML) is the Azure Machine Learning capability that allows users to quickly build, train, and deploy predictive models with minimal or no coding experience.
Automated ML automatically performs tasks that would normally require expert data science knowledge, such as:
Selecting appropriate algorithms (e.g., decision trees, logistic regression, random forests)
Performing hyperparameter tuning to optimize model accuracy
Handling missing data and feature scaling automatically
Generating performance metrics and best model recommendations
This feature is especially useful for business analysts, developers, or beginners who want to leverage machine learning for predictions (like sales forecasting, churn analysis, or demand prediction) without having to write complex Python code.
Other options explained:
A. ML pipelines automate and organize workflows for model training and deployment but still require pre-built models.
B. Copilot is an AI-powered assistant embedded in Microsoft tools for productivity, not a model training feature.
C. DALL-E is an image generation model under Azure OpenAI, not a predictive modeling tool.
Thus, per official Microsoft Learn content, Automated Machine Learning is the correct capability to quickly build and deploy predictive models with minimal coding.
You need to create a model that labels a collection of your personal digital photographs.
Which Azure Al service should you use?
Azure Al Language
Azure Al Computer Vision
Azure Al Document Intelligence
Azure Al Custom Vision
According to the Microsoft Azure AI Fundamentals (AI-900) official study materials and Microsoft Learn module “Describe features of Computer Vision workloads on Azure”, the Azure AI Custom Vision service allows users to build, train, and deploy custom image classification or object detection models. It is specifically designed for scenarios where you need a model tailored to your unique image dataset — in this case, personal digital photographs.
Custom Vision lets you upload and label your own images (for example, “family,” “friends,” “vacations,” or “pets”) and then train a model that learns to recognize those categories. The system automatically extracts relevant features from the training images and creates a model capable of classifying new images into the predefined labels. You can iteratively refine your model by adding more images or re-training to improve accuracy.
The other options do not fit this requirement:
A. Azure AI Language deals with text-based tasks such as language understanding, sentiment analysis, and key phrase extraction — not image processing.
B. Azure AI Computer Vision provides prebuilt image analysis models (e.g., object detection, tag generation, scene description), but it cannot learn custom categories unique to your dataset. It’s great for general image recognition but not for specialized labeling tasks.
C. Azure AI Document Intelligence (Form Recognizer) is used to extract information from structured or semi-structured documents such as forms, invoices, or receipts — not photographs.
Therefore, when you need to label or categorize personal photos with custom-defined tags, the right service is Azure AI Custom Vision, because it allows you to build a model trained specifically on your own collection of images.
You need to create a training dataset and validation dataset from an existing dataset.
Which module in the Azure Machine Learning designer should you use?
Select Columns in Dataset
Add Rows
Split Data
Join Data
In Azure Machine Learning designer, the Split Data module is specifically designed to divide a dataset into training and validation (or testing) subsets. The AI-900 study guide and the Microsoft Learn module “Split data for training and evaluation” explain that this module allows users to control how data is partitioned, ensuring that models are trained on one portion of the data and tested on unseen data to assess performance.
By default, the Split Data module uses a 70/30 or 80/20 ratio, meaning 70–80% of the data is used for training and the remaining 20–30% for validation or testing. This ensures the model’s generalizability and prevents overfitting.
The other options serve different purposes:
A. Select Columns in Dataset: Used to choose specific columns or features from a dataset.
B. Add Rows: Combines multiple datasets vertically.
D. Join Data: Combines datasets horizontally based on a common key.
Only Split Data performs the function of dividing data into training and validation subsets.
You need to use Azure Machine Learning designer to build a model that will predict automobile prices.
Which type of modules should you use to complete the model? To answer, drag the appropriate modules to the correct locations. Each module 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 selection is worth one point.
Box 1: Select Columns in Dataset
For Columns to be cleaned, choose the columns that contain the missing values you want to change. You can choose multiple columns, but you must use the same replacement method in all selected columns.
Example:
The task is to build a machine learning model in Azure Machine Learning designer to predict automobile prices, which is a regression problem since the output (price) is a continuous numeric value. The pipeline must follow the logical data preparation, training, and evaluation flow as outlined in the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn module “Create a machine learning model with Azure Machine Learning designer.”
Here’s the correct sequence and reasoning:
Select Columns in Dataset:The first step after loading the raw automobile dataset is to choose the relevant columns that will be used as features (inputs) and the label (output). This module ensures that only necessary fields (for example, horsepower, engine size, mileage, etc.) are used to train the model while excluding irrelevant columns like vehicle ID or serial number.
Split Data:Next, the cleaned and filtered dataset must be split into two subsets: training data and testing data (often 70/30 or 80/20). This allows the model to be trained on one portion and evaluated on the other to measure predictive accuracy.
Linear Regression:Since automobile price prediction is a numeric prediction task, the appropriate learning algorithm is Linear Regression. This supervised algorithm learns relationships between numeric features and the target (price).
Finally, the workflow connects the training data and Linear Regression module to the Train Model module, which outputs a trained regression model. The trained model is then linked to the Score Model module to compare predicted vs. actual prices.
This pipeline fully aligns with Microsoft’s recommended process for regression in Azure ML Designer.
You need to develop a web-based AI solution for a customer support system. Users must be able to interact with a web app that will guide them to the best resource or answer.
Which service should you integrate with the web app to meet the goal?
Azure Al Language Service
Face
Azure Al Translator
Azure Al Custom Vision
QnA Maker is a cloud-based API service that lets you create a conversational question-and-answer layer over your existing data. Use it to build a knowledge base by extracting questions and answers from your semistructured content, including FAQs, manuals, and documents. Answer users’ questions with the best answers from the QnAs in your knowledge base—automatically. Your knowledge base gets smarter, too, as it
continually learns from user behavior.
What should you use to extract details from scanned images of contracts?
Azure Al Document Intelligence
Azure Al Immersive Reader
Azure OpenAI
Azure Al Search
The correct answer is A. Azure AI Document Intelligence (previously known as Form Recognizer). This Azure Cognitive Service is specifically designed to extract structured data and key information from scanned documents, forms, and contracts using advanced Optical Character Recognition (OCR) combined with machine learning models.
According to the Microsoft Learn module “Extract data from documents with Azure AI Document Intelligence”, this service enables automated data extraction from unstructured or semi-structured documents such as contracts, invoices, receipts, and purchase orders. It identifies key-value pairs, tables, and fields such as names, dates, amounts, and signatures. This makes it ideal for digitizing legal and business documents like contracts into structured formats that can be easily searched or stored in databases.
Azure AI Document Intelligence offers several model types:
Prebuilt models for common documents (invoices, receipts, business cards, etc.).
Custom models trained on your specific contract layouts.
Layout model for extracting raw text, tables, and structures.
The other options are incorrect:
B. Azure AI Immersive Reader enhances reading comprehension and accessibility but does not extract data from documents.
C. Azure OpenAI provides natural language generation and understanding but is not used for scanning or data extraction.
D. Azure AI Search indexes and searches textual or document content but relies on other services (like Document Intelligence) to extract the data first.
Therefore, to automatically extract details such as contract terms, names, dates, and signatures from scanned contract images, the best Microsoft AI service is A. Azure AI Document Intelligence
Select the answer that correctly completes the sentence.
This question is drawn from the Microsoft Azure AI Fundamentals (AI-900) syllabus section “Describe features of natural language processing (NLP) workloads on Azure.” According to the Microsoft Learn materials, Natural Language Processing (NLP) is a branch of artificial intelligence that allows computers to analyze, understand, and generate human language. NLP enables machines to work with text or speech data in a way that extracts meaning, sentiment, and intent.
Microsoft defines NLP as enabling scenarios such as language detection, text classification, key phrase extraction, sentiment analysis, and named entity recognition. The example given—classifying emails as “work-related” or “personal”—is a text classification task, which falls under NLP capabilities. The AI model processes the textual content of emails, identifies linguistic patterns, and categorizes them based on the detected topic or context.
Let’s analyze the other options:
Predict the number of future car rentals → This is a forecasting task, handled by machine learning regression models, not NLP.
Predict which website visitors will make a transaction → This is a classification or prediction problem in machine learning, not NLP, since it deals with behavioral or numerical data rather than language.
Stop a process in a factory when extremely high temperatures are registered → This is an IoT or anomaly detection scenario, focusing on sensor data, not language understanding.
Therefore, only classifying email messages as work-related or personal correctly represents an NLP use case. It illustrates how NLP can analyze written text and make intelligent categorizations—a key capability covered in AI-900’s natural language workloads section.
In which two scenarios can you use speech recognition? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
an in-car system that reads text messages aloud
providing closed captions for recorded or live videos
creating an automated public address system for a train station
creating a transcript of a telephone call or meeting
The correct answers are B and D.
Speech recognition, part of Azure’s Speech service, converts spoken audio into written text. It is a core feature of Azure Cognitive Services for speech-to-text scenarios.
Providing closed captions for recorded or live videos (B) – This is a typical application of speech recognition. The AI system listens to audio content from a video and generates real-time or post-event captions. Azure’s Speech-to-Text API is frequently used in broadcasting and video platforms to improve accessibility and searchability.
Creating a transcript of a telephone call or meeting (D) – Another common use case is automated transcription. The Speech service can process real-time audio streams (such as meetings or calls) and produce accurate text transcripts. This is widely used in customer service, call analytics, and meeting documentation.
The incorrect options are:
A. an in-car system that reads text messages aloud – This uses Text-to-Speech, not speech recognition.
C. creating an automated public address system for a train station – This also uses Text-to-Speech, since it generates spoken output from text.
Therefore, scenarios that convert spoken words into text correctly represent speech recognition, making B and D the right answers.
Which two actions can you perform by using the Azure OpenAI DALL-E model? Each correct answer presents a complete solution.
NOTE: Each correct answer is worth one point.
Create images.
Use optical character recognition (OCR).
Detect objects in images.
Modify images.
Generate captions for images.
The correct answers are A. Create images and D. Modify images.
The Azure OpenAI DALL-E model is a text-to-image generative AI model that can create original images and modify existing ones based on text prompts. According to Microsoft Learn and Azure OpenAI documentation, DALL-E interprets natural language descriptions to produce unique and creative visual content, making it useful for design, illustration, marketing, and educational applications.
Create images (A) – DALL-E can generate new images entirely from textual input. For example, the prompt “a futuristic city skyline at sunrise” would result in a custom-generated artwork that visually represents that description.
Modify images (D) – DALL-E also supports inpainting and outpainting, allowing users to edit or expand existing images. You can replace parts of an image (for example, changing a background or object) or add new elements consistent with the visual style of the original.
The remaining options are incorrect:
B. OCR is performed by Azure AI Vision, not DALL-E.
C. Detect objects in images is also an Azure AI Vision (Image Analysis) feature.
E. Generate captions for images is handled by Azure AI Vision, not DALL-E, since DALL-E generates—not interprets—visuals.
Select the answer that correctly completes the sentence.
The correct answer is Azure AI Language, which includes the Question Answering capability (previously known as QnA Maker). According to the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn documentation, the Azure AI Language service can be used to create a knowledge base from frequently asked questions (FAQ) and other structured or semi-structured text sources.
This service allows developers to build intelligent applications that can understand and respond to user questions in natural language by referencing prebuilt or custom knowledge bases. The Question Answering feature extracts pairs of questions and answers from documents, websites, or manually entered data and uses them to construct a searchable knowledge base. This knowledge base can then be integrated with Azure Bot Service or other conversational platforms to create interactive, self-service chatbots.
Here’s how it works:
Developers upload FAQ documents, URLs, or structured content.
Azure AI Language processes the content and identifies logical question-answer pairs.
The model stores these pairs in a knowledge base that can be queried by user input.
When users ask questions, the model finds the best matching answer using natural language understanding techniques.
In contrast:
Azure AI Document Intelligence (Form Recognizer) is used to extract structured data from forms and documents, not to create FAQ knowledge bases.
Azure AI Bot Service is for managing and deploying conversational bots but does not generate knowledge bases.
Microsoft Bot Framework SDK provides tools for building conversational logic but still requires a knowledge source like Question Answering from Azure AI Language.
Therefore, the service that can create a knowledge base from FAQ content is Azure AI Language.
For each of The following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
The Azure AI Language service (part of Azure Cognitive Services) provides a set of natural language processing (NLP) capabilities designed to analyze and interpret text data. Its core features include language detection, key phrase extraction, sentiment analysis, and named entity recognition (NER).
Language Identification – YESAccording to the Microsoft Learn module “Analyze text with Azure AI Language,” one of the service’s built-in capabilities is language detection, which determines the language of a given text string (e.g., English, Spanish, or French). This allows applications to automatically adapt to multilingual input.
Handwritten Signature Detection – NOThe Azure AI Language service only processes text-based data; it does not analyze images or handwriting. Detecting handwritten signatures requires computer vision capabilities, specifically Azure AI Vision or Azure AI Document Intelligence, which can extract and interpret visual content from scanned documents or images.
Identifying Companies and Organizations – YESThe Named Entity Recognition (NER) feature within Azure AI Language can identify entities such as people, locations, dates, organizations, and companies mentioned in text. It tags these entities with categories, enabling structured analysis of unstructured data.
✅ Summary:
Language detection → Yes (supported by AI Language).
Handwritten signatures → No (requires Computer Vision).
Entity recognition for companies/organizations → Yes (supported by AI Language NER).
You need to determine the location of cars in an image so that you can estimate the distance between the cars.
Which type of computer vision should you use?
optical character recognition (OCR)
object detection
image classification
face detection
Object detection is similar to tagging, but the API returns the bounding box coordinates (in pixels) for each object found. For example, if an image contains a dog, cat and person, the Detect operation will list those objects together with their coordinates in the image. You can use this functionality to process the relationships between the objects in an image. It also lets you determine whether there are multiple instances of the same tag in an image.
The Detect API applies tags based on the objects or living things identified in the image. There is currently no formal relationship between the tagging taxonomy and the object detection taxonomy. At a conceptual level, the Detect API only finds objects and living things, while the Tag API can also include contextual terms like " indoor " , which can ' t be localized with bounding boxes.
You are developing a conversational AI solution that will communicate with users through multiple channels including email, Microsoft Teams, and webchat.
Which service should you use?
Text Analytics
Azure Bot Service
Translator
Form Recognizer
According to the Microsoft Azure AI Fundamentals official study guide and Microsoft Learn module “Describe features of conversational AI workloads on Azure”, Azure Bot Service is the core Azure platform for building, testing, deploying, and managing conversational agents or chatbots. These bots can communicate with users across multiple channels, including email, Microsoft Teams, Slack, Facebook Messenger, and webchat.
Azure Bot Service integrates deeply with the Bot Framework SDK and Azure Cognitive Services such as Language Understanding (LUIS) or Azure AI Language, enabling natural language processing and multi-channel message delivery. The service abstracts away channel management, meaning that developers can build one bot logic that connects seamlessly to several communication platforms.
Option analysis:
A. Text Analytics is a Cognitive Service used for text mining tasks like key phrase extraction, language detection, and sentiment analysis — not for building chatbots.
C. Translator provides language translation but cannot manage conversations or multi-channel delivery.
D. Form Recognizer extracts structured information from documents and forms — unrelated to conversational interaction.
The AI-900 course explicitly defines Azure Bot Service as “a managed platform that enables intelligent, multi-channel conversational experiences between users and bots.” This service allows businesses to unify chat experiences across multiple digital communication channels.
Thus, based on the official Microsoft Learn content and AI-900 syllabus, the best and verified answer is B. Azure Bot Service, as it is the designated Azure solution for deploying a single conversational AI experience accessible from multiple platforms such as email, Teams, and webchat.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
This question tests understanding of Microsoft’s six guiding principles for Responsible AI, which are: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. These principles, as described in the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn Responsible AI module, help ensure that AI systems are developed and used ethically and responsibly.
Transparency – Yes:Transparency means users should understand how and why an AI system makes certain decisions. Providing an explanation of the outcome of a credit loan application clearly supports transparency because it helps customers know the reasoning behind approval or rejection. According to Microsoft Learn, transparency ensures that “AI systems are understandable by users and stakeholders,” especially in sensitive applications such as finance and credit scoring. Thus, the first statement is Yes.
Reliability and Safety – Yes:The reliability and safety principle ensures AI systems perform consistently, safely, and as intended, even in complex or high-risk environments. A triage bot that prioritizes insurance claims based on injury type aligns with this principle—it must be accurate, dependable, and safe to ensure claims are processed correctly and not influenced by errors or faulty algorithms. Microsoft teaches that AI should be “reliable under expected and unexpected conditions” to prevent harm or misjudgment. Therefore, this statement is Yes.
Inclusiveness – No:Inclusiveness focuses on ensuring AI systems empower and benefit all users, especially those with different abilities or backgrounds. Offering an AI solution at different prices across sales territories is a business decision, not an ethical or inclusiveness principle issue. It does not relate to accessibility or equal participation of diverse users. Therefore, this final statement is No.
To complete the sentence, select the appropriate option in the answer area.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Identify features and uses of speech capabilities”, speech recognition refers to the process of converting spoken words into written text. When a speaker’s voice is transcribed into subtitles during a presentation, the system listens to the audio input, identifies the spoken words, and generates corresponding text in real time. This is precisely what speech recognition technology accomplishes.
Azure provides this functionality through the Azure Speech Service, which supports multiple speech-related features:
Speech-to-Text (Speech Recognition) – Converts spoken audio into text.
Text-to-Speech (Speech Synthesis) – Converts written text into spoken audio.
Speech Translation – Translates spoken words into another language.
In this case, the session is transcribed into subtitles in the same language, not translated or spoken aloud, so the correct feature is Speech Recognition.
Let’s review the other options:
Sentiment Analysis: This belongs to the Text Analytics service under natural language processing (NLP) and is used to determine the emotional tone of text, not to convert speech to text.
Speech Synthesis: Converts text into audible speech (Text-to-Speech), the reverse of what is happening in this scenario.
Translation: Converts spoken or written words from one language to another. Here, no translation is mentioned—only transcription.
Therefore, the described process—turning live spoken language into readable subtitles—is an example of Speech Recognition, a speech-to-text AI capability provided by Azure Cognitive Services.
Final Answer: Speech recognition
A medical research project uses a large anonymized dataset of brain scan images that are categorized into predefined brain haemorrhage types.
You need to use machine learning to support early detection of the different brain haemorrhage types in the images before the images are reviewed by a person.
This is an example of which type of machine learning?
clustering
regression
classification
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Identify features of classification machine learning”, classification is a supervised machine learning technique used when the output variable represents discrete categories or classes. In this case, the brain scan images are already labeled into predefined haemorrhage types, such as “subarachnoid,” “epidural,” or “intraventricular.” The model’s goal is to learn patterns from labeled examples and then predict the correct class for new, unseen images.
The use of categorized brain scan images clearly indicates a supervised learning setup because both the input (image data) and output (haemorrhage type) are known during training. This aligns with Microsoft’s definition: classification problems “predict which category or class an item belongs to,” often using algorithms such as logistic regression, decision trees, neural networks, or convolutional neural networks (CNNs) for image-based data.
In contrast:
A. Clustering is an unsupervised learning approach that groups data into clusters based on similarity when no predefined labels exist.
B. Regression predicts continuous numeric values (e.g., predicting age or temperature), not categories.
Because this project aims to automatically classify medical images into known diagnostic categories, it is a textbook example of classification.
You build a QnA Maker bot by using a frequently asked questions (FAQ) page.
You need to add professional greetings and other responses to make the bot more user friendly.
What should you do?
Increase the confidence threshold of responses
Enable active learning
Create multi-turn questions
Add chit-chat
According to the Microsoft Learn module “Build a QnA Maker knowledge base”, QnA Maker allows developers to create bots that answer user queries based on documents like FAQs or manuals. To make a bot more natural and conversational, Microsoft provides a “chit-chat” feature — a prebuilt, professionally written set of responses to common conversational phrases such as greetings (“Hello”), small talk (“How are you?”), and polite phrases (“Thank you”).
Adding chit-chat improves user experience by making the bot sound friendlier and more human-like. It doesn’t alter the main Q & A logic but enhances the bot’s tone and responsiveness.
The other options are not correct:
A. Increase the confidence threshold makes the bot more selective in responses but doesn’t add new conversational features.
B. Enable active learning improves knowledge base accuracy over time through user feedback.
C. Create multi-turn questions adds conversational flow for related topics but doesn’t add greetings or casual dialogue.
Thus, to make the bot more personable, the correct action is to Add chit-chat.
What are two tasks that can be performed by using computer vision? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
Predict stock prices.
Detect brands in an image.
Detect the color scheme in an image
Translate text between languages.
Extract key phrases.
According to the Microsoft Azure AI Fundamentals study guide and Microsoft Learn module “Identify features of computer vision workloads”, computer vision is an AI workload that allows systems to interpret and understand visual information from the world, such as images and videos.
Computer vision tasks typically include:
Object detection and image classification (e.g., detecting brands, logos, or items in images)
Image analysis (e.g., identifying colors, patterns, or visual features)
Face detection and recognition
Optical Character Recognition (OCR) for reading text in images
Therefore, both detecting brands and detecting color schemes in an image are clear examples of computer vision tasks because they involve analyzing visual content.
In contrast:
A. Predict stock prices → Regression task, not vision-based.
D. Translate text between languages → Natural language processing (NLP).
E. Extract key phrases → NLP as well.
Thus, the correct computer vision tasks are B and C.
Stating the source of the data used to train a model is an example of which responsible Al principle?
fairness
transparency
reliability and safety
privacy and security
According to Microsoft’s Responsible AI Principles, Transparency means that AI systems should clearly communicate how they operate, including data sources, limitations, and decision-making processes. Stating the source of data used to train a model helps users understand where the model’s knowledge comes from, enabling informed trust and accountability.
Transparency ensures that organizations disclose relevant details about data collection and model design, especially for compliance, fairness, and reproducibility.
Other options are incorrect:
A. Fairness: Focuses on avoiding bias and ensuring equitable outcomes.
C. Reliability and safety: Ensures AI performs consistently and safely.
D. Privacy and security: Protects user data and maintains confidentiality.
Thus, the principle illustrated by disclosing training data sources is Transparency.
Match the Al workload to the appropriate task.
To answer, drag the appropriate Ai workload from the column on the left to its task on the right. Each workload may be used once, more than once, or not at all.
NOTE: Each correct match is worth one point.
This question tests your understanding of AI workloads as described in the Microsoft Azure AI Fundamentals (AI-900) study guide. Each Azure AI workload is designed to handle specific types of data and tasks: text, images, documents, or content generation.
Extract data from medical admission forms for import into a patient tracking database → Azure AI Document IntelligenceFormerly known as Form Recognizer, this service belongs to the Azure AI Document Intelligence workload. It extracts key-value pairs, tables, and textual information from structured and semi-structured documents such as forms, invoices, and admission sheets. For medical forms, Document Intelligence can identify fields like patient name, admission date, and diagnosis and export them into structured formats for database import.
Automatically create drafts for a monthly newsletter → Generative AIThis task involves creating original written content, which is a capability of Generative AI. Microsoft’s Azure OpenAI Service uses large language models (like GPT-4) to generate human-like text, summaries, or articles. Generative AI workloads are ideal for automating creative writing, drafting newsletters, producing blogs, or summarizing reports.
Analyze aerial photos to identify flooded areas → Computer VisionComputer Vision workloads involve analyzing and interpreting visual data from images or videos. This includes detecting objects, classifying scenes, and identifying patterns such as flooded regions in aerial imagery. Azure’s Computer Vision or Custom Vision services can be trained to detect water coverage or terrain changes using image recognition techniques.
Thus, the correct matches are:
Azure AI Document Intelligence → Extract medical form data
Generative AI → Create newsletter drafts
Computer Vision → Identify flooded areas from aerial photos
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
The Translator service, part of Microsoft Azure Cognitive Services, is designed specifically for text translation between multiple languages. It is a cloud-based neural machine translation service that supports more than 100 languages. According to Microsoft Learn’s module “Translate text with the Translator service”, this service provides two main capabilities: text translation and automatic language detection.
“You can use the Translator service to translate text between languages.” → YesThis statement is true. The primary purpose of the Translator service is to translate text accurately and efficiently between supported languages, such as English to Spanish or French to Japanese. It maintains contextual meaning using neural machine translation models.
“You can use the Translator service to detect the language of a given text.” → YesThis statement is also true. The Translator service includes automatic language detection, which determines the source language before translation. For instance, if a user submits text in an unknown language, the service can identify it automatically before performing translation.
“You can use the Translator service to transcribe audible speech into text.” → NoThis statement is false. Transcribing speech (audio) into text is a function of the Azure Speech service, specifically the Speech-to-Text API, not the Translator service.
Therefore, the Translator service is used for text translation and language detection, while speech transcription belongs to the Speech service.
What can be used to complete a paragraph based on a sentence provided by a user?
Azure Al Language
Azure OpenAI
Azure Machine Learning
Azure Al Vision
The service that can complete a paragraph based on a sentence is Azure OpenAI. According to Microsoft Learn’s AI-900 study guide, Azure OpenAI provides access to advanced language models like GPT-3.5 and GPT-4, which can generate and continue text, summarize, or create content based on prompts. The task described—text completion—is precisely what GPT models are designed for.
Azure AI Language performs language understanding and analysis (sentiment, key phrases, translation), Azure Machine Learning trains custom models, and Azure AI Vision handles images. Hence, Azure OpenAI is the correct choice.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
In Microsoft Azure AI Language Service, both Named Entity Recognition (NER) and Key Phrase Extraction are core features for text analytics. They serve distinct purposes in analyzing and structuring unstructured text data.
Named Entity Recognition (NER):NER is used to identify and categorize specific entities within text, such as people, organizations, locations, dates, times, and quantities. According to Microsoft Learn’s “Analyze text with Azure AI Language” module, NER scans text to extract these entities along with their types. Therefore, the statement “Named entity recognition can be used to retrieve dates and times in a text string” is True (Yes).
Key Phrase Extraction:This feature identifies the most important phrases or main topics in a block of text. It is useful for summarization or highlighting central ideas without classifying them into specific categories. Therefore, the statement “Key phrase extraction can be used to retrieve important phrases in a text string” is also True (Yes).
City Name Retrieval:While key phrase extraction highlights major phrases, it does not extract specific entities like cities or dates. Extracting such details requires Named Entity Recognition, which is designed to find named entities such as city names, people, or organizations. Hence, the statement “Key phrase extraction can be used to retrieve all the city names in a text string” is False (No).
Which Azure service can use the prebuilt receipt model in Azure Al Document Intelligence?
Azure Al Computer Vision
Azure Machine Learning
Azure Al Services
Azure Al Custom Vision
The prebuilt receipt model is part of Azure AI Document Intelligence (formerly Form Recognizer), which belongs to the broader Azure AI Services family. The prebuilt receipt model is designed to automatically extract key information such as merchant names, dates, totals, and tax amounts from receipts without requiring custom training.
Among the given options, C. Azure AI Services is correct because it encompasses all cognitive AI capabilities—vision, language, speech, and document processing. Specifically, Azure AI Document Intelligence is included within Azure AI Services and provides both prebuilt and custom models for processing invoices, receipts, business cards, and identity documents.
Options A (Computer Vision) and D (Custom Vision) are image-based services, not form-processing tools. Option B (Azure Machine Learning) focuses on building custom predictive models, not using prebuilt document models.
Therefore, the correct answer is C. Azure AI Services, which includes the prebuilt receipt model in Document Intelligence.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE; Each correct selection is worth one point.
The Azure OpenAI DALL-E model is a generative image model designed to create original images from textual descriptions (prompts). According to the Microsoft Learn documentation and the AI-900 study guide, DALL-E’s primary function is text-to-image generation—it converts creative or descriptive text input into visually relevant imagery.
“Generate captions for uploaded images” → NoDALL-E cannot create image captions. Captioning an image (describing what’s in an uploaded image) is a vision analysis task, not an image generation task. That functionality belongs to Azure AI Vision, which can analyze and describe images, detect objects, and generate captions automatically.
“Reliably generate technically accurate diagrams” → NoWhile DALL-E can create visually appealing artwork or conceptual sketches, it is not designed for producing precise or technically correct diagrams, such as engineering schematics or architectural blueprints. The model’s generative process emphasizes creativity and visual diversity rather than factual or geometric accuracy. Thus, it cannot be relied upon for professional technical outputs.
“Generate decorative images to enhance learning materials” → YesThis is one of DALL-E’s strongest use cases. It can generate decorative, conceptual, or illustrative images to enhance presentations, educational materials, and marketing content. It enables educators and designers to quickly produce unique visuals aligned with specific themes or topics, enhancing engagement and creativity.
You plan to apply Text Analytics API features to a technical support ticketing system.
Match the Text Analytics API features to the appropriate natural language processing scenarios.
To answer, drag the appropriate feature from the column on the left to its scenario on the right. Each feature may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
Box1: Sentiment analysis
Sentiment Analysis is the process of determining whether a piece of writing is positive, negative or neutral.
Box 2: Broad entity extraction
Broad entity extraction: Identify important concepts in text, including key
Key phrase extraction/ Broad entity extraction: Identify important concepts in text, including key phrases and named entities such as people, places, and organizations.
Box 3: Entity Recognition
Named Entity Recognition: Identify and categorize entities in your text as people, places, organizations, date/time, quantities, percentages, currencies, and more. Well-known entities are also recognized and linked to more information on the web.
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.
This question is based on identifying Natural Language Processing (NLP) workloads, which is a fundamental topic in the Microsoft Azure AI Fundamentals (AI-900) certification. According to the official Microsoft Learn module “Describe features of natural language processing (NLP) workloads on Azure”, NLP enables computers to understand, interpret, and generate human language — both written and spoken.
A bot that responds to queries by internal users – YesThis is an example of a natural language processing workload because it involves understanding and generating human language. A chatbot interprets user input (queries written or spoken) using language understanding and text analytics, and then produces appropriate responses. On Azure, this can be implemented using Azure AI Language (LUIS) and the Azure Bot Service, both core NLP technologies.
A mobile application that displays images relating to an entered search term – NoThis application involves searching for or displaying images, which falls under the computer vision workload, not NLP. Computer vision focuses on analyzing and interpreting visual data like photos or videos, while NLP deals with language and text processing.
A web form used to submit a request to reset a password – NoA password reset form involves structured input fields and user authentication, not natural language understanding or generation. It’s part of standard web development and identity management, not an NLP-related process.
Therefore, based on Microsoft’s AI-900 curriculum definitions:
✅ The only true NLP example is the bot responding to user queries, since it processes and understands natural language input to generate conversational output.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Statement
Yes / No
Providing an explanation of the outcome of a credit loan application is an example of the Microsoft transparency principle for responsible AI.
Yes
A triage bot that prioritizes insurance claims based on injuries is an example of the Microsoft reliability and safety principle for responsible AI.
Yes
An AI solution that is offered at different prices for different sales territories is an example of the Microsoft inclusiveness principle for responsible AI.
No
This question is based on the Responsible AI principles defined by Microsoft, which are part of the AI-900 Microsoft Azure AI Fundamentals curriculum. Microsoft’s Responsible AI framework consists of six key principles: Fairness, Reliability and Safety, Privacy and Security, Inclusiveness, Transparency, and Accountability. Each principle ensures that AI systems are developed and used in a way that benefits people and society responsibly.
Transparency Principle – YesProviding an explanation for a loan decision aligns with the Transparency principle. Microsoft defines transparency as helping users and stakeholders understand how AI systems make decisions. For example, when a credit scoring AI model approves or denies a loan, explaining the factors that influenced that outcome (such as credit history or income level) ensures that customers understand the reasoning process. This builds trust and supports responsible deployment.
Reliability and Safety Principle – YesA triage bot that prioritizes insurance claims based on injury severity relates directly to Reliability and Safety. This principle ensures AI systems operate consistently, perform accurately, and produce dependable outcomes. In the case of the triage bot, it must reliably assess the input data (injury descriptions) and rank claims appropriately to avoid harm or misjudgment, aligning with Microsoft’s emphasis on designing AI systems that are safe and robust.
Inclusiveness Principle – NoAn AI solution priced differently across sales territories is not related to Inclusiveness. Inclusiveness focuses on ensuring accessibility and eliminating bias or exclusion for all users—especially those with disabilities or underrepresented groups. Pricing strategy is a business decision, not an inclusiveness issue. Therefore, this statement is No.
In summary, based on the AI-900 Responsible AI principles, the correct selections are:
Which Azure Al Language feature can be used to retrieve data, such as dates and people ' s names, from social media posts?
language detection
speech recognition
key phrase extraction
entity recognition
The Azure AI Language service provides several NLP features, including language detection, key phrase extraction, sentiment analysis, and named entity recognition (NER).
When you need to extract specific data points such as dates, names, organizations, or locations from unstructured text (for example, social media posts), the correct feature is Entity Recognition.
Entity Recognition identifies and classifies information in text into predefined categories like:
Person names (e.g., “John Smith”)
Organizations (e.g., “Contoso Ltd.”)
Dates and times (e.g., “October 22, 2025”)
Locations, events, and quantities
This capability helps transform unstructured textual data into structured data that can be analyzed or stored.
Option analysis:
A (Language detection): Determines the language of a text (e.g., English, French).
B (Speech recognition): Converts spoken audio to text; not applicable here.
C (Key phrase extraction): Identifies important phrases or topics but not specific entities like names or dates.
D (Entity recognition): Correctly extracts names, dates, and other specific data from text.
Hence, the accurate feature for this scenario is D. Entity Recognition.
You plan to deploy an Azure Machine Learning model by using the Machine Learning designer
Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Identify features of common machine learning types”, the standard workflow for creating and deploying a machine learning model — especially within Azure Machine Learning Designer — follows a structured sequence of steps to ensure that the model is trained effectively and evaluated correctly.
Here’s the detailed breakdown of the correct order:
Import and prepare a dataset:This is always the first step in the machine learning lifecycle. The dataset is imported into Azure Machine Learning and cleaned or preprocessed. Preparation might include handling missing values, normalizing data, removing outliers, and encoding categorical variables. This ensures the dataset is ready for modeling.
Split the data randomly into training data and validation data:The dataset is then divided into two parts — the training set and the validation (or testing) set. Typically, around 70–80% of the data is used for training and 20–30% for validation. This step ensures that the model can be evaluated on unseen data later, preventing overfitting.
Train the model:During this stage, the machine learning algorithm learns patterns from the training data. Azure Machine Learning Designer provides multiple algorithms (classification, regression, clustering, etc.) that can be applied using “Train Model” components.
Evaluate the model against the validation dataset:Finally, the trained model’s performance is tested using the validation dataset. Evaluation metrics such as accuracy, precision, recall, or RMSE (depending on the model type) are calculated to assess how well the model generalizes to new data.
The incorrect option — “Evaluate the model against the original dataset” — is not used in proper ML workflows, because evaluating on the same data used for training would give misleadingly high accuracy due to overfitting.
You have an Azure Machine Learning model that predicts product quality. The model has a training dataset that contains 50,000 records. A sample of the data is shown in the following table.
For each of the following Statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
This question tests the understanding of features and labels in machine learning, a core concept covered in the Microsoft Azure AI Fundamentals (AI-900) syllabus under “Describe fundamental principles of machine learning on Azure.”
In supervised machine learning, data is divided into features (inputs) and labels (outputs).
Features are the independent variables — measurable properties or characteristics used by the model to make predictions.
Labels are the dependent variables — the target outcome the model is trained to predict.
From the provided dataset, the goal of the Azure Machine Learning model is to predict product quality (Pass or Fail). Therefore:
Mass (kg) is a feature – Yes“Mass (kg)” represents an input variable used by the model to learn patterns that influence product quality. It helps the algorithm understand how variations in mass might correlate with passing or failing the quality test. Thus, it is correctly classified as a feature.
Quality Test is a label – YesThe “Quality Test” column indicates the outcome of the manufacturing process, marked as either Pass or Fail. This is the target the model tries to predict during training. In Azure ML terminology, this column is the label, as it represents the dependent variable.
Temperature (C) is a label – No“Temperature (C)” is an input that helps the model determine quality outcomes, not the outcome itself. It influences the quality result but is not the value being predicted. Therefore, temperature is another feature, not a label.
In conclusion, per Microsoft Learn and AI-900 study materials, features are measurable inputs (like mass and temperature), while the label is the target output (like the quality test result).
Match the types of machine learning to the appropriate scenarios.
To answer, drag the appropriate machine learning type from the column on the left to its scenario on the right. Each machine learning type may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Describe features of common AI workloads”, there are three primary supervised and unsupervised machine learning types: Regression, Classification, and Clustering. Each type of learning addresses a different kind of problem depending on the data and desired prediction output.
Regression – Regression models are used to predict numeric, continuous values. The study guide specifies that “regression predicts a number.” In the scenario “Predict how many minutes late a flight will arrive based on the amount of snowfall,” the output (minutes late) is a continuous numeric value. Therefore, this is a regression problem. Regression algorithms like linear regression or decision tree regression estimate relationships between variables and predict measurable quantities.
Clustering – Clustering falls under unsupervised learning, where the model identifies natural groupings or patterns in unlabeled data. The official AI-900 training material states that “clustering is used to find groups or segments of data that share similar characteristics.” The scenario “Segment customers into different groups to support a marketing department” fits this description because the goal is to group customers based on behavior or demographics without predefined labels. Thus, it is a clustering problem.
Classification – Classification is a supervised learning method used to predict discrete categories or labels. The AI-900 content defines classification as “predicting which category an item belongs to.” The scenario “Predict whether a student will complete a university course” requires a yes/no (binary) outcome, which is a classic classification problem. Examples include logistic regression, decision trees, or neural networks trained for categorical prediction.
In summary:
Regression → Predicts continuous numeric outcomes.
Clustering → Groups data by similarities without predefined labels.
Classification → Predicts discrete or categorical outcomes.
Hence, the correct and verified mappings based on the official AI-900 study material are:
Regression → Flight delay prediction
Clustering → Customer segmentation
Classification → Course completion prediction
Select the answer that correctly completes the sentence.
Text extraction.
According to the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn documentation for Azure AI Vision (formerly Computer Vision), text extraction—also known as Optical Character Recognition (OCR)—is the computer vision capability that detects and extracts printed or handwritten text from images and video frames.
In this scenario, a traffic monitoring system collects vehicle registration numbers (license plates) from CCTV footage. These registration numbers are alphanumeric text that must be read and converted into digital form for processing, storage, or analysis. The Azure AI Vision service’s OCR (text extraction) feature performs this function. It analyzes each frame from the video feed, detects text regions (the license plates), and converts the visual text into machine-readable text data.
This process is widely used in Automatic Number Plate Recognition (ANPR) systems that support law enforcement, toll booths, and parking management solutions. The OCR model can handle variations in font, lighting, and angle to accurately extract license plate numbers.
The other options describe different vision capabilities:
Image classification assigns an image to a general category (e.g., “car,” “truck,” or “bike”), not text extraction.
Object detection identifies and locates objects in images using bounding boxes (e.g., detecting the car itself), but not the text written on the car.
Spatial analysis tracks people or objects in a defined physical space (e.g., counting individuals entering a building), not reading text.
Therefore, for a traffic monitoring system that identifies vehicle registration numbers from CCTV footage, the most accurate Azure AI Vision capability is Text extraction (OCR).
You need to predict the income range of a given customer by using the following dataset.
Which two fields should you use as features? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
Education Level
Last Name
Age
Income Range
First Name
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Describe core concepts of machine learning on Azure”, when building a predictive machine learning model, features are the input variables used by the algorithm to predict the target label. The target label is the output or value the model is trained to predict.
In this dataset, the target variable is clearly the Income Range, since the goal is to predict a customer’s income bracket. Therefore, Income Range (D) is the label, not a feature. Features must be other attributes that help the model make this prediction.
The fields Education Level (A) and Age (C) are the most relevant features because both can logically and statistically influence income level.
Education Level is a categorical variable that often correlates strongly with income. Individuals with higher education levels tend to earn more on average, making this an important predictor.
Age is a numerical variable that typically affects income level due to factors such as experience and career progression.
By contrast:
First Name (E) and Last Name (B) are irrelevant as features because they are identifiers, not meaningful predictors of income. Including them could lead to bias or model overfitting without contributing to accurate predictions.
Hence, according to AI-900 principles, the features used to train a model predicting income range would be Education Level and Age.
Which term is used to describe uploading your own data to customize an Azure OpenAI model?
completion
grounding
fine -tuning
prompt engineering
In Azure OpenAI Service, fine-tuning refers to the process of uploading your own labeled dataset to customize or adapt a pretrained model (such as GPT-3.5 or Curie) for a specific use case. According to the Microsoft Learn documentation and AI-900 official study guide, fine-tuning allows organizations to improve a model’s performance on domain-specific tasks or to align responses with brand tone and context.
Fine-tuning differs from simple prompting because it requires providing structured training data (usually in JSONL format) that contains pairs of input prompts and ideal completions. The model uses this data to adjust its internal weights, thereby “learning” your organization’s language patterns, terminology, or industry context.
Option review:
A. Completion: Refers to the text generated by a model in response to a prompt. It’s the output, not the customization process.
B. Grounding: Integrates external, up-to-date data sources (like search results or databases) during inference but doesn’t alter the model’s parameters.
C. Fine-tuning: ✅ Correct — this is the process of uploading and training with your own data.
D. Prompt engineering: Involves designing effective prompts but does not change the underlying model.
Thus, fine-tuning is the term used for customizing an Azure OpenAI model using your own uploaded data.
To complete the sentence, select the appropriate option in the answer area.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Prepare data for machine learning”, feature engineering refers to the process of transforming raw data into meaningful features that can be effectively used by machine learning algorithms. This includes steps such as scaling, normalization, encoding categorical variables, handling missing values, and creating new features derived from existing ones.
The question states:
“Ensuring that the numeric variables in training data are on a similar scale.”
This directly describes a data normalization or standardization step, which is a core component of feature engineering. The purpose of scaling numeric variables is to ensure that all features contribute equally to the model’s learning process. Without normalization, features with large numeric ranges (such as “income in dollars”) could dominate smaller-scale features (like “age in years”), leading to biased model performance.
In Azure Machine Learning, this is typically done using the Normalize Data module or transformations in the data preparation stage. Microsoft Learn explains that normalization and feature scaling are applied before model training to ensure that gradient-based algorithms (such as regression or neural networks) converge more efficiently and produce more accurate results.
The other options are not correct:
Data ingestion refers to collecting and importing data into a system.
Feature selection involves choosing the most relevant features, not scaling them.
Model training is the phase where the algorithm learns patterns from the processed data, which occurs after feature engineering.
Therefore, ensuring that numeric variables are on a similar scale is a step in Feature Engineering.
In which two scenarios can you use a speech synthesis solution? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
an automated voice that reads back a credit card number entered into a telephone by using a numeric keypad
generating live captions for a news broadcast
extracting key phrases from the audio recording of a meeting
an Al character in a computer game that speaks audibly to a player
According to the Microsoft Learn module “Explore speech capabilities of Azure AI” and the AI-900 Official Study Guide, speech synthesis (also known as text-to-speech) is the process of converting written text into spoken audio output. Azure’s Speech service provides this functionality, allowing applications to produce human-like voices dynamically.
Let’s evaluate each scenario:
A. Automated voice that reads back a credit card number entered into a telephone keypad → YesThis is a classic text-to-speech (TTS) use case. The application converts numeric or textual input (such as a credit card number) into audio output that the caller hears. Azure Speech service can handle such voice responses in automated phone systems or IVR (Interactive Voice Response) setups.
B. Generating live captions for a news broadcast → NoThis is a speech-to-text scenario (speech recognition), not speech synthesis. It involves converting audio speech into written text.
C. Extracting key phrases from an audio recording of a meeting → NoThis involves speech-to-text followed by text analytics, not speech synthesis.
D. An AI character in a computer game that speaks audibly to a player → YesThis is a direct example of speech synthesis, where the character’s dialog text is converted into realistic spoken output for immersive interaction.
Therefore, based on Microsoft’s AI-900 curriculum, speech synthesis is used in applications that convert text into audible speech, such as automated voice systems or interactive digital characters.
Select the answer that correctly completes the sentence.
In the Microsoft Azure AI Fundamentals (AI-900) curriculum, computer vision capabilities refer to artificial intelligence systems that can analyze and interpret visual content such as images and videos. The Azure AI Vision and Face API services provide pretrained models for detecting, recognizing, and analyzing visual information, enabling developers to build intelligent applications that understand what they " see. "
When asked how computer vision capabilities can be deployed, the correct answer is to integrate a face detection feature into an app. This aligns with Microsoft Learn’s module “Describe features of computer vision workloads,” which explains that computer vision can identify objects, classify images, detect faces, and extract text (OCR). The Face API, a part of Azure AI Vision, specifically provides face detection, verification, and emotion recognition capabilities.
Integrating these services into an application allows it to perform actions such as:
Detecting human faces in photos or video streams.
Recognizing facial attributes like age, emotion, or head pose.
Enabling secure authentication based on face recognition.
The other options are incorrect because they relate to different AI workloads:
Develop a text-based chatbot for a website: This falls under Conversational AI, implemented with Azure Bot Service or Conversational Language Understanding (CLU).
Identify anomalous customer behavior on an online store: This task relates to machine learning and anomaly detection models, not computer vision.
Suggest automated responses to incoming email: This uses Natural Language Processing (NLP) capabilities, not visual analysis.
Therefore, the correct and Microsoft-verified completion of the statement is:
“Computer vision capabilities can be deployed to integrate a face detection feature into an app.”
You have a database that contains a list of employees and their photos.
You are tagging new photos of the employees.
For each of the following statements select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
These answers are derived from the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module “Explore computer vision in Microsoft Azure.” The Azure Face service, part of Azure Cognitive Services, provides advanced facial recognition capabilities including detection, verification, identification, grouping, and similarity analysis.
Let’s analyze each statement:
“The Face service can be used to group all the employees who have similar facial characteristics.” → YesThe Face service supports a grouping function that automatically organizes a collection of unknown faces into groups based on visual similarity. It doesn’t require labeled data; instead, it identifies clusters of similar-looking faces. This is particularly useful when building or validating datasets of people.
“The Face service will be more accurate if you provide more sample photos of each employee from different angles.” → YesAccording to Microsoft documentation, model accuracy improves when you provide multiple high-quality images of each person under different conditions—such as varying lighting, poses, and angles. This diversity allows the service to better learn unique facial characteristics and improves recognition reliability, especially for identification and verification tasks.
“If an employee is wearing sunglasses, the Face service will always fail to recognize the employee.” → NoThis is incorrect. While occlusions (like sunglasses or hats) can reduce accuracy, the service may still recognize the person depending on how much of the face remains visible. Microsoft Learn explicitly notes that partial occlusion affects recognition confidence but does not guarantee failure.
In conclusion, the Face service can group similar faces (Yes), become more accurate with diverse samples (Yes), and still recognize partially covered faces though with lower confidence (No). These principles align directly with the Face API’s core functions and AI-900 learning objectives regarding computer vision and responsible AI-based facial recognition.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Azure Bot Service and Azure Cognitive Services can be integrated. → Yes
Azure Bot Service engages with customers in a conversational manner. → Yes
Azure Bot Service can import frequently asked questions (FAQ) to question and answer sets. → Yes
\
All three statements are true, as confirmed by the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Explore conversational AI.” The Azure Bot Service is Microsoft’s platform for building, deploying, and managing intelligent bots that can communicate naturally with users across various channels (web, Teams, Facebook Messenger, etc.).
Azure Bot Service and Azure Cognitive Services can be integrated → YesMicrosoft Learn specifies that Azure Bot Service can be enhanced with Azure Cognitive Services such as Language Understanding (LUIS), QnA Maker, and Speech Services to add intelligence. For example, integration with LUIS allows bots to understand user intent and context, while QnA Maker helps them respond accurately to FAQs. As stated in the official documentation: “The Azure Bot Service can be combined with Cognitive Services to create bots that understand language, speech, and meaning.”
Azure Bot Service engages with customers in a conversational manner → YesThe primary function of Azure Bot Service is to create conversational AI agents that interact naturally with users. These bots simulate human-like dialogue using text or speech. According to Microsoft Learn, “Bots created using Azure Bot Service communicate with users in a conversational format through natural language.”
Azure Bot Service can import frequently asked questions (FAQ) to question and answer sets → YesAzure Bot Service can integrate with the QnA Maker (now part of Azure Cognitive Service for Language) to automatically import FAQs from existing documents or web pages and generate a knowledge base of question-answer pairs. This allows the bot to respond intelligently to customer queries.
In conclusion, Azure Bot Service supports intelligent, conversational interaction, integrates seamlessly with Cognitive Services, and can use QnA Maker to import and manage FAQ-based knowledge sets—making all three statements true.
Match the Al solution to the appropriate task.
To answer, drag the appropriate solution from the column on the left to its task on the right. Each solution may be used once, more than once, or not at all.
NOTE: Each correct match is worth one point.
This question evaluates your understanding of how different Azure AI workloads correspond to specific tasks in image, text, and content generation scenarios, as explained in the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn modules covering common AI workloads and Azure services.
Generate a caption from a given image → Computer VisionThis is a computer vision task because it involves analyzing the visual elements of an image and producing descriptive text (a caption). Azure AI Vision provides image analysis and captioning capabilities through its Describe Image API, which uses deep learning models to recognize objects, scenes, and actions in an image and automatically generate natural-language descriptions (e.g., “A cat sitting on a sofa”).
Generate an image from a given caption → Generative AIThis task belongs to Generative AI, which focuses on creating new content such as text, code, or images based on prompts. Tools like Azure OpenAI Service with DALL-E can interpret text descriptions and generate realistic images that match the given caption. Generative AI is capable of creative synthesis, not just analysis, making it the appropriate category.
Generate a 200-word summary from a 2,000-word article → Text AnalyticsText analytics (a subset of natural language processing) allows summarization, sentiment analysis, and entity recognition from large text corpora. Azure AI Language includes text summarization capabilities that condense long documents into concise summaries while preserving meaning and key information.
You have a dataset that contains the columns shown in the following table.
You have a machine learning model that predicts the value of ColumnE based on the other numeric columns.
Which type of model is this?
regression
analysis
clustering
The dataset described contains numeric columns (ColumnA through ColumnE). The model’s task is to predict the value of ColumnE based on the other numeric columns (A–D). This is a classic regression problem.
According to the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn module “Identify common types of machine learning,” a regression model is used when the target variable (the value to predict) is continuous and numeric, such as price, temperature, or—in this case—a numerical value in ColumnE.
Regression models analyze relationships between independent variables (inputs: Columns A–D) and a dependent variable (output: ColumnE) to predict a continuous outcome. Common regression algorithms include linear regression, decision tree regression, and neural network regression.
Option analysis:
A. Regression: ✅ Correct. Used for predicting numerical, continuous values.
B. Analysis: ❌ Incorrect. “Analysis” is a general term, not a machine learning model type.
C. Clustering: ❌ Incorrect. Clustering is unsupervised learning, grouping similar data points, not predicting values.
Therefore, the type of machine learning model used to predict ColumnE (a numeric value) from other numeric columns is Regression, which fits perfectly within Azure’s supervised learning models.
Select the answer that correctly completes the sentence.
The correct answer is “An embedding.”
In the context of large language models (LLMs) such as GPT-3, GPT-3.5, or GPT-4, an embedding refers to a multi-dimensional numeric vector representation assigned to each word, token, or phrase. According to the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn documentation for Azure OpenAI embeddings, embeddings are used to represent textual or semantic meaning in a numerical form that a machine learning model can process mathematically.
Each embedding captures the semantic relationships between words. Words or tokens with similar meanings (for example, “car” and “automobile”) are represented by vectors that are close together in the multi-dimensional space, while unrelated words (like “tree” and “laptop”) are farther apart. This vector representation enables the model to understand context, similarity, and relationships between different pieces of text.
Embeddings are fundamental in tasks such as:
Semantic search: Finding documents or sentences with similar meaning.
Clustering: Grouping related concepts together.
Recommendation systems: Suggesting similar content based on text meaning.
Contextual understanding: Helping generative models produce coherent and context-aware text.
Option review:
Attention: A mechanism used within transformers to focus on relevant parts of input sequences but not a representation of words.
A completion: Refers to the generated text output from a model, not the internal representation.
A transformer: The architecture that powers models like GPT, not the vector representation of tokens.
Therefore, the correct term for a multi-dimensional vector assigned to each word or token in a large language model (LLM) is An embedding, which represents how meaning is numerically encoded and compared within language models.
To complete the sentence, select the appropriate option in the answer area.
According to Microsoft’s Responsible AI principles, one of the key guiding values is Reliability and Safety, which ensures that AI systems operate consistently, accurately, and safely under all intended conditions. The AI-900 study materials and Microsoft Learn modules explain that an AI system must be trustworthy and dependable, meaning it should not produce results when the input data is incomplete, corrupted, or significantly outside the expected range.
In the given scenario, the AI system avoids providing predictions when important fields contain unusual or missing values. This behavior demonstrates reliability and safety because it prevents the system from making unreliable or potentially harmful decisions based on bad or insufficient data. Microsoft emphasizes that AI systems must undergo extensive validation, testing, and monitoring to ensure stable performance and predictable outcomes, even when data conditions vary.
The other options do not fit this scenario:
Inclusiveness ensures that AI systems are accessible to and usable by all people, regardless of abilities or backgrounds.
Privacy and Security focuses on protecting user data and ensuring it is used responsibly.
Transparency involves making AI decisions explainable and understandable to humans.
Only Reliability and Safety directly address the concept of an AI system refusing to act or returning an error when it cannot make a trustworthy prediction. This principle helps prevent inaccurate or unsafe outputs, maintaining confidence in the system’s integrity.
Therefore, ensuring an AI system does not produce predictions when input data is incomplete or unusual aligns directly with Microsoft’s Reliability and Safety principle for responsible AI.
To complete the sentence, select the appropriate option in the answer area.
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module “Explore natural language processing (NLP) in Azure”, Natural Language Processing (NLP) is a branch of artificial intelligence that focuses on enabling computers to understand, interpret, and generate human language. NLP is used to extract meaning and intent from text or speech, perform sentiment analysis, identify entities, and classify content based on context.
One of the primary applications of NLP is text classification, where an AI model automatically categorizes text documents or messages into predefined classes. Classifying emails as work-related or personal is a textbook example of this NLP capability. It involves analyzing the words, phrases, and structure of the text to determine the email’s category. Microsoft Learn highlights this type of problem as document classification, an essential NLP use case often implemented through Azure Cognitive Services such as Text Analytics or Language Studio.
Let’s examine why the other options are incorrect:
Predict the number of future car rentals – This is a time series forecasting or regression task, not NLP.
Predict which website visitors will make a transaction – This is a predictive analytics or machine learning classification problem based on behavioral data, not language understanding.
Stop a process in a factory when extremely high temperatures are registered – This relates to IoT automation or sensor-based anomaly detection, not NLP.
Therefore, based on Microsoft’s AI-900 materials, Natural Language Processing is best used for tasks involving understanding and classifying text, such as classifying email messages as work-related or personal. This example perfectly aligns with NLP’s goal—to enable machines to process and derive insights from human language inputs.
For a machine learning progress, how should you split data for training and evaluation?
Use features for training and labels for evaluation.
Randomly split the data into rows for training and rows for evaluation.
Use labels for training and features for evaluation.
Randomly split the data into columns for training and columns for evaluation.
https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/split-data
The correct answer is B. Randomly split the data into rows for training and rows for evaluation.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Describe fundamental principles of machine learning on Azure”, the process of developing a machine learning model involves dividing the available dataset into two or more parts—commonly training data and evaluation (or testing) data. The goal is to ensure that the model can learn patterns from one subset of the data (training set) and then be objectively tested on unseen data (evaluation set) to measure how well it generalizes to new situations.
The training dataset contains both features (the measurable inputs) and labels (the target outputs). The model learns from the patterns and relationships between these features and labels. The evaluation dataset also contains features and labels, but it is kept separate during the training phase. Once the model has been trained, it is tested on this unseen evaluation data to calculate metrics like accuracy, precision, recall, or F1 score.
Microsoft emphasizes that the data split should be random and based on rows, not columns. Each row represents a complete observation (for example, one customer record, one transaction, or one image). Randomly splitting ensures that both subsets represent the same distribution of data, avoiding bias. Splitting by columns would separate features themselves, which would make the model training invalid.
The AI-900 materials often illustrate this using Azure Machine Learning’s data preparation workflow, where data is randomly divided (commonly 70% for training and 30% for testing). This ensures the model learns from diverse examples and is fairly evaluated.
Therefore, the verified and correct approach, as per Microsoft’s official guidance, is B. Randomly split the data into rows for training and rows for evaluation.
Your website has a chatbot to assist customers.
You need to detect when a customer is upset based on what the customer types in the chatbot.
Which type of AI workload should you use?
anomaly detection
semantic segmentation
regression
natural language processing
According to the Microsoft Azure AI Fundamentals (AI-900) curriculum and Microsoft Learn module “Explore natural language processing”, NLP enables computers to understand, interpret, and analyze human language. One of its key capabilities is sentiment analysis, which detects emotional tone (positive, negative, or neutral) in text.
In this scenario, the chatbot must detect when a customer is upset based on what they type. This directly maps to sentiment analysis, a core NLP function. The Text Analytics service within Azure Cognitive Services provides prebuilt sentiment analysis models that return a sentiment score and classification (e.g., positive, neutral, negative). As per Microsoft Learn, “Natural language processing allows systems to understand sentiment and intent within text and speech to derive meaningful insights.”
Explanation of other options:
A. Anomaly detection identifies unusual patterns in data (e.g., fraud detection), not emotions in text.
B. Semantic segmentation is a computer vision technique used to label pixels in an image.
C. Regression predicts continuous numeric values and is not related to understanding text or emotions.
Therefore, to enable the chatbot to detect when a user is upset based on text input, the correct AI workload is Natural Language Processing (NLP), specifically through Azure Text Analytics sentiment analysis.
Select the answer that correctly completes the sentence.
This question refers to a system that monitors a user’s emotions or expressions—in this case, identifying whether a kiosk user is annoyed—through a video feed. According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Identify Azure services for computer vision,” this scenario falls under facial analysis, which is a capability of Azure AI Vision or the Face API.
Facial analysis involves detecting human faces in images or video and analyzing facial features to interpret emotions, expressions, age, gender, or facial landmarks. The AI model does not try to identify who the person is but rather interprets how they appear or feel. For example, facial analysis can detect emotions such as happiness, anger, sadness, or surprise, which allows applications to infer a user’s engagement or frustration level while interacting with a system.
Option review:
Face detection: Identifies the presence and location of a face in an image but does not interpret expressions or emotions.
Facial recognition: Matches a detected face to a known individual’s identity (for authentication or security), not for emotion detection.
Optical character recognition (OCR): Extracts text from images or scanned documents and has no relation to human emotion or facial features.
Therefore, determining whether a kiosk user is annoyed, happy, or frustrated involves emotion detection within facial analysis, making Facial analysis the correct answer.
This aligns with AI-900’s definition of computer vision workloads, where facial analysis provides insights into emotions and expressions, supporting user experience optimization and customer behavior analytics.
Copyright © 2014-2026 Certensure. All Rights Reserved