AI-900 Practice Test 44 — 15 Questions

Question 1

A company wants to build a self-service FAQ bot that answers customer questions based on a collection of policy documents (PDFs and Word files). They want the bot to extract answers directly from the documents without manually creating question-answer pairs. Which Azure AI Language feature should they use?

Accepted Answer

Custom Question Answering. Custom Question Answering (C) is the correct choice because it is specifically designed to extract answers directly from source documents (PDFs, Word files) without requiring manual creation of question-answer pairs. It uses a deep learning-based extractive reader to locate answer spans within the text, making it ideal for building a self-service FAQ bot from policy documents.

Answer

Key Phrase Extraction

Answer

Conversational Language Understanding (CLU)

Answer

Azure OpenAI on your data

Question 2

What is the primary benefit of using Retrieval Augmented Generation (RAG) over relying solely on an LLM's trained knowledge?

Accepted Answer

RAG grounds LLM responses in current, specific information — reducing hallucination and knowledge cutoff issues. RAG enhances LLM outputs by retrieving relevant, up-to-date information from an external knowledge base (e.g., Azure Cognitive Search) and injecting it into the prompt context. This grounds the model's response in verifiable data, significantly reducing hallucinations and overcoming the knowledge cutoff limitation inherent in static training data.

Answer

RAG makes LLMs faster by skipping the training process

Answer

RAG reduces the cost of API calls by batching requests

Answer

RAG allows LLMs to process images alongside text

Question 3

A data scientist trains a regression model to predict housing prices. The model uses polynomial features up to degree 5. It achieves an R-squared of 0.95 on the training set but only 0.60 on the test set. Which problem is the model most likely experiencing?

Accepted Answer

Overfitting. The model performs exceptionally well on the training data (R-squared 0.95) but poorly on the test data (R-squared 0.60), which is the classic symptom of overfitting. Using polynomial features up to degree 5 introduces high model complexity, causing the model to learn noise and specific patterns in the training set that do not generalize to unseen data.

Answer

Underfitting

Answer

Data leakage

Answer

Multicollinearity

Question 4

A company uses Azure OpenAI to generate marketing copy. They want to ensure that the generated text does not contain inappropriate or harmful content before it is published. Which Azure OpenAI feature is specifically designed for this purpose?

Accepted Answer

Content filters. Content filters are the Azure OpenAI feature specifically designed to detect and block inappropriate or harmful content in generated text. They apply configurable severity levels across categories like hate, violence, self-harm, and sexual content, ensuring outputs meet safety policies before publication.

Answer

Temperature

Answer

Top-p (nucleus sampling)

Answer

System message

Question 5

What is the purpose of Azure AI Language's 'personally identifiable information (PII) detection' feature?

Accepted Answer

Identifying and extracting personal information (names, addresses, ID numbers) from text for redaction. Option B is correct because Azure AI Language's PII detection feature is designed to identify and extract personally identifiable information such as names, addresses, phone numbers, and ID numbers from unstructured text. This allows organizations to redact or mask sensitive data before further processing or storage, helping to comply with privacy regulations like GDPR and HIPAA.

Answer

Generating fake personal information for testing applications

Answer

Verifying the identity of users accessing AI services

Answer

Encrypting personal information stored in databases

Question 6

A company is developing an AI voice assistant for children. The assistant must respond with age-appropriate language and avoid providing any harmful instructions. Which Microsoft responsible AI principle is most directly relevant to ensuring the system operates safely?

Accepted Answer

Reliability and Safety. The scenario requires the AI voice assistant to avoid providing harmful instructions and to operate safely for children. Microsoft's Reliability and Safety principle directly addresses the need for systems to function reliably and to fail safely, preventing harm even when unexpected inputs occur. This principle ensures that the assistant's responses are vetted for safety, which is the most relevant consideration here.

Answer

Fairness

Answer

Privacy and Security

Answer

Inclusiveness

Question 7

A data scientist trains a machine learning model on historical sales data to predict future sales volume. The model achieves 99% accuracy on the training dataset but only 75% accuracy on a separate test dataset. What is the most likely issue with this model?

Accepted Answer

Overfitting. The model's 99% accuracy on the training set versus 75% on the test set indicates it has memorized the training data, including noise and outliers, rather than learning generalizable patterns. This classic symptom of overfitting occurs when the model is too complex relative to the amount or variability of the training data, causing poor performance on unseen data.

Answer

Underfitting

Answer

High bias

Answer

High variance

Question 8

A data scientist is training a regression model to predict house prices. The model performs near perfectly on the training data but poorly on a held-out test set. The scientist suspects the model is memorizing the training data instead of learning general patterns. Which technique is most appropriate to directly address this issue?

Accepted Answer

Apply L2 regularization to the model. L2 regularization (also known as Ridge regularization) directly addresses overfitting by adding a penalty term proportional to the square of the model weights to the loss function. This discourages the model from assigning excessively large coefficients to features, forcing it to learn simpler, more general patterns rather than memorizing noise in the training data.

Answer

Increase the size of the training dataset

Answer

Increase the complexity of the model (e.g., add more features)

Answer

Switch to a different regression algorithm

Question 9

A customer support team wants to automatically analyze customer emails to determine if the sentiment is positive, negative, or neutral. Which Azure service should they use?

Accepted Answer

Text Analytics. The Text Analytics service (part of Azure Cognitive Services) provides pre-built sentiment analysis, which can classify text as positive, negative, or neutral. This directly matches the requirement to automatically analyze customer emails for sentiment without needing to build custom machine learning models.

Answer

Speech

Answer

Translator

Answer

QnA Maker

Question 10

What is the purpose of system messages in Azure OpenAI API calls?

Accepted Answer

Developer-provided instructions that define the AI's role and behavioral constraints for a session. System messages in Azure OpenAI API calls are developer-provided instructions that define the AI's role, tone, and behavioral constraints for the entire session. They act as a persistent meta-prompt that guides the model's responses, ensuring consistency and alignment with the application's requirements.

Answer

Technical error messages returned by the API when something goes wrong

Answer

Messages sent by the operating system to alert of resource usage

Answer

Notifications sent to users when the AI service is experiencing issues

Question 11

A bank is developing an AI system to automatically approve or reject small business loan applications. The bank wants to ensure that the system does not unfairly discriminate against applicants based on their age, gender, or ethnicity. Which Microsoft responsible AI principle should most directly guide the design and evaluation of this system?

Accepted Answer

Fairness. The bank's goal is to prevent discrimination based on age, gender, or ethnicity in loan approvals. The Fairness principle directly addresses this by requiring AI systems to treat all groups equitably and to mitigate biases in training data and model predictions. This principle guides the design and evaluation of the system to ensure that outcomes are not skewed by protected attributes.

Answer

Reliability and safety

Answer

Privacy and security

Answer

Inclusiveness

Question 12

A hospital is deploying an AI system that recommends treatment plans based on patient data. The chief medical officer insists that doctors must be able to understand why the AI recommended a specific treatment. Which Microsoft responsible AI principle is most directly relevant to this requirement?

Accepted Answer

Transparency. Transparency is the responsible AI principle that requires AI systems to be understandable and interpretable by humans. In this scenario, the chief medical officer's demand that doctors must understand why the AI recommended a specific treatment directly aligns with transparency, which includes providing explanations for model outputs, such as feature importance or decision paths, to enable clinical validation and trust.

Answer

Reliability and safety

Answer

Fairness

Answer

Accountability

Question 13

A company analyzes customer reviews to identify common themes. They need to automatically extract the most important concepts from each review, such as 'battery life', 'customer service', and 'price'. Which Azure AI Language feature should they use?

Accepted Answer

Key phrase extraction. Key phrase extraction is the correct Azure AI Language feature because it automatically identifies and extracts the most important concepts, such as 'battery life', 'customer service', and 'price', from unstructured text like customer reviews. It returns a list of key phrases that represent the main topics discussed, which directly matches the requirement to extract important concepts.

Answer

Sentiment analysis

Answer

Language detection

Answer

Named entity recognition

Question 14

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 15

A company wants to build a chatbot that answers customer questions using only their internal knowledge base, which consists of several PDFs and Word documents. They do not want the chatbot to use any information from the model's pre-trained knowledge. Which Azure OpenAI feature should they use to achieve this?

Accepted Answer

Azure OpenAI on your data. Azure OpenAI on your data allows you to connect Azure OpenAI models to your own data sources (such as PDFs and Word documents) and restrict the model to generate responses solely from that data, without using the model's pre-trained knowledge. This is achieved by indexing the documents into an Azure Cognitive Search index and using retrieval-augmented generation (RAG) to ground the model's responses in your specific content.

Answer

Content filtering

Answer

Prompt flow

Answer

Temperature parameter