AI-900 Practice Test 25 — 15 Questions

Question 1

What is 'AI for accessibility' and what Azure AI services support it?

Accepted Answer

Using speech, vision, and language AI to remove barriers for people with disabilities. 'AI for accessibility' refers to using AI technologies—specifically speech, vision, and language services—to create inclusive solutions that remove barriers for people with disabilities. Azure AI services such as Azure Cognitive Services (e.g., Computer Vision for image descriptions, Speech-to-Text for real-time captioning, and Translator for language translation) directly enable these accessibility scenarios, aligning with Microsoft's commitment to inclusive design.

Answer

Making AI services accessible to small businesses through affordable pricing

Answer

Providing accessible APIs with clear documentation for developer communities

Answer

Ensuring AI applications work on low-bandwidth connections in developing regions

Question 2

What is 'Azure AI Foundry' and what is its primary purpose?

Accepted Answer

A unified enterprise platform for building, evaluating, and deploying AI applications with the full development lifecycle. Azure AI Foundry is a unified enterprise platform that provides an integrated environment for building, evaluating, and deploying AI applications across the full development lifecycle. It combines tools for data preparation, model training, evaluation, and deployment, enabling teams to manage AI projects from ideation to production within a single interface.

Answer

A physical Microsoft facility for AI hardware manufacturing

Answer

A subscription tier that includes all Azure AI services at a fixed monthly price

Answer

A training platform specifically for AI engineers at Microsoft

Question 3

A developer uses Azure OpenAI to generate product descriptions. The outputs often repeat the same phrases multiple times within a single description. Which parameter should the developer increase to reduce this repetition?

Accepted Answer

Frequency penalty. The frequency penalty parameter reduces repetition by penalizing tokens that have already appeared in the generated text. Increasing this value discourages the model from reusing the same phrases, making the output more diverse and less repetitive.

Answer

Temperature

Answer

Presence penalty

Answer

Max tokens

Question 4

What is 'active learning' in Azure Machine Learning data labelling?

Accepted Answer

Strategically selecting the most informative examples for human labelling to maximise learning efficiency. Active learning in Azure Machine Learning data labelling is a technique where the model identifies the data points it is most uncertain about and prioritizes those for human review. This strategic selection maximizes the learning efficiency of the model by ensuring that each labelled example provides the highest possible information gain, reducing the total number of labels needed.

Answer

Having users actively participate in model training by rating AI responses

Answer

A training approach where the model actively searches the internet for additional training data

Answer

Continuous model training that runs actively in the background as new data arrives

Question 5

What is 'feature engineering' and why does it matter for machine learning models?

Accepted Answer

Creating and transforming input variables using domain knowledge to improve model performance. Feature engineering is the process of creating new input variables or transforming existing ones using domain knowledge to help machine learning models better capture patterns in the data. It directly impacts model performance by making the underlying relationships more explicit, reducing noise, and enabling algorithms to learn more effectively. In Azure Machine Learning, this is often done through automated feature engineering tools or custom Python scripts within pipelines.

Answer

Building physical infrastructure features (GPU clusters) for model training

Answer

The process of selecting which machine learning algorithm to use for a task

Answer

Adding new computing nodes to a training cluster to speed up training

Question 6

A city's traffic department wants to predict the number of cars that will cross a particular bridge each day to plan maintenance schedules. The output of the model should be a numerical value representing the estimated traffic count. Which type of machine learning task is this?

Accepted Answer

Regression. Regression is the correct type of machine learning task because the goal is to predict a continuous numerical value—the number of cars crossing the bridge each day. Unlike classification, which predicts discrete categories, regression models output a real number, making it ideal for forecasting traffic counts.

Answer

Classification

Answer

Clustering

Answer

Reinforcement learning

Question 7

A data scientist trains a regression model to predict house prices using features like bedrooms, square footage, and location. The model achieves a low error on the training data but performs significantly worse when used to predict prices in a new city with different property characteristics. Which concept best explains this poor performance?

Accepted Answer

Overfitting. The model performs well on training data but poorly on new data from a different city, which is the classic symptom of overfitting. Overfitting occurs when a model learns noise and specific patterns in the training data that do not generalize to unseen data, especially when the new data has different characteristics (e.g., different property market dynamics). In this case, the model has memorized the training city's price patterns rather than learning generalizable relationships.

Answer

Underfitting

Answer

Data leakage

Answer

Bias-variance tradeoff

Question 8

What is the Azure AI Face service's 'liveness detection' feature used for?

Accepted Answer

Determining whether a face is from a live person or a spoofing attempt (photo/video/mask). Azure AI Face's liveness detection is specifically designed to differentiate between a real, live human face and spoofing artifacts such as printed photos, video replays, or 3D masks. It analyzes subtle cues like micro-movements, texture, and depth to verify the presence of a living person, preventing unauthorized access in facial recognition systems.

Answer

Detecting whether a person is alive based on their vital signs

Answer

Counting how many people are in a live video stream

Answer

Monitoring whether a person remains present during a video call

Question 9

What is the purpose of 'top_p' (nucleus sampling) in Azure OpenAI API calls?

Accepted Answer

A sampling method that restricts token selection to the most probable token set. 'top_p' (nucleus sampling) in Azure OpenAI API calls controls the cumulative probability threshold for token selection. Instead of considering all possible next tokens, the model selects from the smallest set of tokens whose cumulative probability exceeds the 'top_p' value (e.g., 0.9 means the model considers only the top tokens that together have a 90% chance). This reduces randomness while allowing more natural variation than fixed 'top_k' sampling.

Answer

The maximum number of paragraphs in the generated response

Answer

A parameter that sets the minimum response quality threshold

Answer

The priority level of the API request in a queue

Question 10

A company's HR department wants to create a self-service bot that can answer employee questions about company policies. They have a collection of policy documents in PDF format. Which Azure AI Language feature should they use to ingest these documents and enable the bot to provide answers based on them?

Accepted Answer

Custom Question Answering. Custom Question Answering (CQA) is the correct choice because it is specifically designed to ingest documents (including PDFs) and build a knowledge base of question-answer pairs. The bot can then query this knowledge base to provide answers based on the policy documents, using the underlying Azure Cognitive Search and language models to match user questions to the most relevant content.

Answer

Sentiment Analysis

Answer

Key Phrase Extraction

Answer

Language Detection

Question 11

What is an AI agent in the context of Azure AI and generative AI?

Accepted Answer

An autonomous system using an LLM to plan and execute multi-step tasks using tools. An AI agent in Azure AI and generative AI contexts refers to an autonomous system that leverages a large language model (LLM) to reason, plan, and execute multi-step tasks by calling external tools or APIs. This aligns with the Azure AI Agent Service, which enables agents to orchestrate workflows, retrieve information, and perform actions without continuous human intervention, embodying the core concept of agentic AI.

Answer

A human employee who manages AI model deployments

Answer

A monitoring agent that checks AI model health automatically

Answer

A software robot that scrapes websites for training data

Question 12

A company wants to use Azure Computer Vision to automatically analyze images of handwritten forms and extract the text for data entry. Which prebuilt Azure Computer Vision capability should they use?

Accepted Answer

Optical Character Recognition (OCR). Azure Computer Vision's Optical Character Recognition (OCR) capability is specifically designed to extract printed or handwritten text from images, including forms. It uses the Read API, which is optimized for text-heavy documents and supports handwritten text recognition, making it the correct choice for this scenario.

Answer

Image Analysis

Answer

Face API

Answer

Object Detection

Question 13

What is 'grounding with Bing search' in Microsoft Copilot?

Accepted Answer

Retrieving current web information from Bing to augment LLM responses beyond its training cutoff. Grounding with Bing search in Microsoft Copilot refers to the technique of retrieving real-time, current web information from Bing to augment the responses of a large language model (LLM) beyond its static training cutoff date. This allows Copilot to provide up-to-date answers on recent events, data, or topics not present in the model's original training corpus, effectively grounding the AI's output in verifiable, live web content.

Answer

Using Bing Maps to provide location-based responses

Answer

Translating Copilot responses using Microsoft's Bing Translator

Answer

Using Bing advertising data to personalize AI responses

Question 14

What is the 'frequency penalty' parameter in Azure OpenAI API calls?

Accepted Answer

A parameter that reduces repetition of words already present in the response. The 'frequency penalty' parameter in Azure OpenAI API calls is designed to reduce the likelihood of the model repeating words or phrases that have already appeared in the generated response. It works by applying a penalty proportional to the frequency of tokens already used, encouraging more diverse and less repetitive text output. This is distinct from the 'presence penalty', which penalizes tokens based on whether they have appeared at all, regardless of frequency.

Answer

A cost multiplier based on how often you call the API

Answer

A rate limiting parameter controlling maximum API calls per minute

Answer

A filter that removes profanity based on how frequently it appears

Question 15

A marketing team uses Azure OpenAI to generate social media posts. They want to ensure the generated text maintains a consistent, predictable brand voice without being overly creative or random. Which parameter should they primarily adjust to control the randomness of the output?

Accepted Answer

Temperature. Temperature controls the randomness of token selection by scaling the logits before applying the softmax function. A lower temperature (e.g., 0.2) makes the model more deterministic and conservative, producing outputs that stick closely to the most likely tokens—ideal for maintaining a consistent, predictable brand voice. Higher temperatures increase randomness, which the team wants to avoid.

Answer

Max tokens

Answer

Frequency penalty

Answer

Top P