AI-900 Practice Test 35 — 15 Questions

Question 1

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 2

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 3

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 4

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 5

A bank uses an AI system to approve personal loans. Some customers whose loans were denied have asked for an explanation of why their application was rejected. Which Microsoft responsible AI principle requires the bank to provide these explanations?

Accepted Answer

Transparency. Transparency is the correct principle because it requires AI systems to be understandable and for decisions to be explainable to users. In this scenario, customers denied loans have a right to know why the AI made that decision, which aligns with Microsoft's principle of transparency—ensuring that AI systems communicate their purpose, limitations, and reasoning in clear, accessible terms.

Answer

Fairness

Answer

Reliability and safety

Answer

Accountability

Question 6

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

Question 7

A company wants to use Azure OpenAI to generate realistic customer conversations for training a chatbot. They have a set of example conversation snippets and want the model to mimic the style and structure of those examples. The company does not want to retrain the model. Which approach should they use?

Accepted Answer

Use prompt engineering with few-shot examples in the prompt. Prompt engineering with few-shot examples allows the model to mimic the style and structure of provided conversation snippets without retraining. By including a few example conversations in the prompt, the model learns the desired pattern through in-context learning, leveraging its pre-trained capabilities to generate realistic customer conversations.

Answer

Fine-tune the model on the conversation dataset

Answer

Use DALL-E to generate the conversations

Answer

Apply a content filter to restrict the output style

Question 8

A data scientist is training a model to predict whether a customer will purchase a product (Yes/No). The dataset contains 90% 'No' and 10% 'Yes'. After training, the model achieves 90% accuracy. Which evaluation metric would be more informative to assess the model's performance on the minority class?

Accepted Answer

F1 score. In this imbalanced dataset (90% 'No', 10% 'Yes'), a model that always predicts 'No' would achieve 90% accuracy, making accuracy a misleading metric. The F1 score is the harmonic mean of precision and recall, specifically designed to evaluate a model's performance on the minority class by balancing false positives and false negatives. It is the most informative metric here because it directly measures how well the model identifies the rare 'Yes' purchases without being inflated by the majority class.

Answer

Mean Absolute Error (MAE)

Answer

Area Under the Curve (AUC)

Answer

R-squared

Question 9

A company uses a large language model to generate answers to employee questions about internal HR policies. However, the model sometimes produces answers that are factually incorrect or not based on the official policies. To reduce these inaccuracies, the company wants to provide the model with relevant, up-to-date policy documents as extra context before generating a response. Which technique is being applied?

Accepted Answer

Grounding with relevant data (RAG). The technique described is Retrieval-Augmented Generation (RAG), which retrieves relevant, up-to-date policy documents from an external knowledge base and provides them as context to the large language model before generating a response. This grounds the model's output in verified data, reducing factual inaccuracies without modifying the model itself. Option C is correct because RAG directly addresses the need to supply extra context from authoritative sources.

Answer

Prompt engineering only

Answer

Fine-tuning the model on policy documents

Answer

Using a content filter

Question 10

What is 'pose estimation' in computer vision and what is it used for?

Accepted Answer

Detecting body keypoint positions (joints) in images to infer posture and movement. Pose estimation is a computer vision technique that detects and localizes keypoints (joints) on a human body in an image or video. These keypoints, such as shoulders, elbows, wrists, hips, and knees, are used to infer the body's posture, orientation, and movement. Option B correctly describes this process of detecting body keypoint positions to infer posture and movement.

Answer

Estimating the correct posture for employees based on ergonomics guidelines

Answer

Determining the camera angle and position used to capture a photograph

Answer

Classifying whether a person is sitting or standing in an image

Question 11

A financial services company uses an AI system to detect fraudulent credit card transactions. After deployment, the system incorrectly flags a significant number of legitimate transactions as fraudulent, causing customer dissatisfaction. The company wants to reduce these false positives while still catching most fraudulent transactions. Which Microsoft responsible AI principle should guide their redesign of the system?

Accepted Answer

Reliability and safety. The Reliability and safety principle emphasizes that AI systems should perform reliably, safely, and consistently under normal conditions. In this scenario, the high rate of false positives indicates the system is not operating reliably for legitimate transactions, causing customer harm. Redesigning to reduce false positives while maintaining fraud detection aligns directly with improving the system's reliability and safety for end users.

Answer

Fairness

Answer

Transparency

Answer

Privacy and security

Question 12

Drag and drop the steps to implement content moderation using Azure Content Moderator into the correct order.

Accepted Answer

Create an Azure Content Moderator resource, submit content for moderation, retrieve moderation results, then take action based on the results.. Content moderation involves setting up the resource, submitting content, reviewing results, and acting.

Answer

Submit content for moderation, create an Azure Content Moderator resource, retrieve moderation results, then take action based on the results.

Answer

Create an Azure Content Moderator resource, retrieve moderation results, submit content for moderation, then take action based on the results.

Answer

Take action based on the results, create an Azure Content Moderator resource, submit content for moderation, retrieve moderation results.

Question 13

What is 'model versioning' and why is it essential in MLOps?

Accepted Answer

Tracking each iteration of a trained model for rollback, A/B testing, auditing, and reproducibility. Model versioning is the practice of tracking each iteration of a trained model, including its hyperparameters, training data snapshot, and evaluation metrics. In MLOps, it is essential because it enables rollback to a previous model if a new version performs poorly, supports A/B testing by comparing multiple model versions in production, provides an audit trail for compliance, and ensures reproducibility by capturing the exact code, data, and environment used to train each version.

Answer

Updating the Python version used to run ML training scripts

Answer

Releasing new features of the Azure ML service as versioned API updates

Answer

Managing multiple versions of training data used by different model experiments

Question 14

A retail company wants to use security cameras to automatically detect when products are removed from shelves. They need to identify the specific product type (e.g., a cereal box, a soda can) and count how many units are taken. Which Azure Computer Vision capability should they use?

Accepted Answer

Object detection. Object detection is the correct capability because it can both locate objects within an image (via bounding boxes) and classify them into specific categories (e.g., cereal box, soda can). This allows the system to identify the product type and count the number of units removed from shelves, which aligns directly with the requirement.

Answer

Optical Character Recognition (OCR)

Answer

Image tagging

Answer

Face detection

Question 15

A customer support team wants to analyze chat transcripts to automatically extract the most frequently mentioned product issues and also determine whether each chat represents a positive, neutral, or negative customer experience. Which prebuilt Azure AI Language feature should they use?

Accepted Answer

A. Text Analytics (prebuilt). The Text Analytics (prebuilt) feature in Azure AI Language provides pre-built capabilities for key phrase extraction (to identify frequently mentioned product issues) and sentiment analysis (to classify chats as positive, neutral, or negative). This matches the customer support team's requirements exactly without needing custom training or complex configuration.

Answer

B. Custom Text Classification

Answer

C. Conversational Language Understanding

Answer

D. Question Answering