AI-900 Practice Test 35 — 15 Questions

Question 1

What is the 'phi' family of models in Azure AI and what makes them distinctive?

Accepted Answer

Small language models from Microsoft Research that achieve strong reasoning performance at compact size. The 'phi' family of models are small language models (SLMs) developed by Microsoft Research that achieve strong reasoning and language understanding performance despite their compact size. They are designed to run efficiently on resource-constrained devices, making them distinctive for edge and offline scenarios where large models are impractical.

Answer

Large multimodal models that process images, audio, and text simultaneously

Answer

Models specialized exclusively for mathematical calculations

Answer

A family of image generation models for creative AI tasks

Question 2

Which of the following is an example of 'anomaly detection' as an AI workload?

Accepted Answer

Automatically identifying fraudulent credit card transactions that deviate from a customer's normal patterns. Anomaly detection identifies data points that deviate significantly from the norm. In this case, fraudulent credit card transactions are detected because they do not match the customer's typical spending patterns, which is a classic use case for anomaly detection in AI workloads.

Answer

Translating customer support emails from Spanish to English

Answer

Generating product descriptions from a list of specifications

Answer

Classifying customer reviews as positive or negative

Question 3

Drag and drop the steps to create a bot with Azure Bot Service into the correct order.

Accepted Answer

Provision Azure Bot Service resource, then develop bot logic, then test the bot locally, then connect to channels.. Creating a bot involves provisioning a resource, developing logic, testing, and connecting channels.

Answer

Develop bot logic, then provision Azure Bot Service resource, then test the bot locally, then connect to channels.

Answer

Provision Azure Bot Service resource, then test the bot locally, then develop bot logic, then connect to channels.

Answer

Connect to channels, then provision Azure Bot Service resource, then develop bot logic, then test the bot locally.

Question 4

Drag and drop the steps to use Azure Speech-to-Text API to transcribe audio into the correct order.

Accepted Answer

Create a Speech resource and obtain subscription key and region, then configure audio input, then initialize a SpeechRecognizer, then call the recognition method and process the result.. Speech-to-text requires a Speech resource, audio input, and API call to return transcription.

Answer

Configure audio input first, then create a Speech resource, then initialize a SpeechRecognizer, then call recognition.

Answer

Create a Speech resource, then initialize a SpeechRecognizer, then configure audio input, then call recognition.

Answer

Create a Speech resource, then call the recognition method, then initialize a SpeechRecognizer, then configure audio input.

Question 5

A logistics company needs to automatically read shipping labels on packages, which include text printed in various fonts and sizes, as well as handwritten addresses. Which Azure Computer Vision capability should they use?

Accepted Answer

Optical Character Recognition (OCR) via the Read API. The Read API is the correct choice because it is specifically designed for extracting printed and handwritten text from images, handling various fonts, sizes, and styles. This makes it ideal for reading shipping labels that contain both machine-printed text and handwritten addresses.

Answer

Dense Captioning

Answer

Image Analysis - Object Detection

Answer

Image Analysis - Tagging

Question 6

A company develops an AI system that screens job applications to recommend candidates for interviews. The system consistently recommends male candidates over equally qualified female candidates. Which Microsoft responsible AI principle is most directly violated?

Accepted Answer

Fairness. The AI system's consistent bias toward male candidates over equally qualified female candidates directly violates the fairness principle, which requires AI systems to treat all people equitably and avoid discrimination based on protected attributes like gender. This is a classic case of algorithmic bias, where the model has learned and perpetuated historical or dataset-driven gender disparities in hiring decisions.

Answer

Reliability and safety

Answer

Privacy and security

Answer

Inclusiveness

Question 7

What is 'recommendation system' as an AI workload and where is it commonly used?

Accepted Answer

AI that predicts user preferences to suggest relevant products, content, or connections. A recommendation system is an AI workload that analyzes historical user behavior, preferences, and item attributes to predict and suggest items a user is likely to be interested in. Option B correctly identifies this as AI that predicts user preferences to suggest relevant products, content, or connections, which is the core definition used in the AI-900 exam.

Answer

An AI that recommends Azure pricing tiers based on an organisation's usage patterns

Answer

A system that recommends when to retrain an AI model based on performance metrics

Answer

AI that recommends the best cloud architecture for a software application

Question 8

Match each Azure AI service to its primary capability.

Accepted Answer

Computer Vision: Extract information from images and videos. Azure AI services are specialized: Computer Vision for images, Speech for audio, Language for text, and Decision for predictive decisions. Common confusions include mixing vision with speech or language with decision.

Answer

Computer Vision: Convert speech to text

Answer

Language: Detect anomalies in data

Question 9

Drag and drop the steps to perform a face detection using Azure Face API into the correct order.

Accepted Answer

Create Azure Face resource and get endpoint/key, then load or reference the image, then send detection request to Face API, then parse the detected face data.. Face detection requires setting up the resource, sending an image, and parsing the detected faces.

Answer

Load or reference the image, then create Azure Face resource and get endpoint/key, then send detection request to Face API, then parse the detected face data.

Answer

Create Azure Face resource and get endpoint/key, then parse the detected face data, then load or reference the image, then send detection request to Face API.

Answer

Send detection request to Face API, then create Azure Face resource and get endpoint/key, then load or reference the image, then parse the detected face data.

Question 10

A data scientist is building a machine learning model to predict the number of daily bike rentals in a city based on weather data and day of the week. The target variable is a continuous integer. Which type of machine learning task is this?

Accepted Answer

Regression. The target variable is the number of daily bike rentals, which is a continuous integer (count). Predicting a continuous numeric value is a regression task. In Azure Machine Learning, regression algorithms such as Linear Regression, Decision Forest Regression, or Poisson Regression are used for this type of problem.

Answer

Classification

Answer

Clustering

Answer

Anomaly Detection

Question 11

What is the Whisper model available in Azure OpenAI used for?

Accepted Answer

Transcribing spoken audio to text with high accuracy across languages. The Whisper model in Azure OpenAI is a large-scale speech recognition system designed to transcribe spoken audio into text. It supports multiple languages and is optimized for high accuracy, making it the correct choice for audio-to-text tasks.

Answer

Generating images from text descriptions

Answer

Generating very quiet (whispering) text-to-speech audio

Answer

Summarizing long documents into concise bullet points

Question 12

Drag and drop the steps to train a custom vision model in Azure Custom Vision into the correct order.

Accepted Answer

Upload tagged images, Train, Evaluate, Publish. Training a custom vision model requires uploading tagged images, training, evaluating, and publishing.

Answer

Train, Upload tagged images, Evaluate, Publish

Answer

Upload tagged images, Evaluate, Train, Publish

Answer

Upload tagged images, Train, Publish, Evaluate

Question 13

Match each Azure AI service to its regional availability constraint.

Accepted Answer

Azure Cognitive Services: Regional availability varies by service and feature.. Regional availability for Azure AI services varies: Cognitive Services have feature-specific limitations, Machine Learning is broadly available but preview features may be restricted, and Bot Service is widely deployed except in some sovereign clouds.

Answer

Azure Cognitive Services: Available in all Azure regions globally without exception.

Answer

Azure Machine Learning: Only available in US East and West Europe.

Answer

Azure Bot Service: Only available in US regions.

Question 14

Match each Azure AI tool to its purpose in the AI lifecycle.

Accepted Answer

Azure Machine Learning: Build, train, and deploy machine learning models. Correct matches: Azure Machine Learning for building/training/deploying models, Azure Cognitive Services for pre-built AI, Azure Bot Service for chatbots, Azure Cognitive Search for AI-powered search. Common confusions include swapping the roles of Machine Learning and Cognitive Services.

Answer

Azure Machine Learning: Add pre-built AI capabilities such as vision, speech, and language

Answer

Azure Cognitive Services: Build, train, and deploy machine learning models

Question 15

What is 'citation' in generative AI and why is it important for trust?

Accepted Answer

Indicating which source documents support an answer — enabling verification and reducing hallucination risk. Citation in generative AI refers to explicitly linking generated content back to specific source documents, which allows users to verify the information and reduces the risk of hallucination by grounding the model's output in verifiable data. This is a key feature in Azure OpenAI Service's 'grounding with your data' capability, where citations are provided alongside responses to build trust and transparency.

Answer

The model citing academic papers when asked about scientific topics

Answer

Quoting user messages back to them to confirm the AI understood the question

Answer

Copyright attribution when the model quotes text from its training data