AI-900 Practice Exam 54 — 20 Questions

Question 1

A customer support team receives thousands of emails daily. They want to automatically route each email to the appropriate department (Billing, Technical Support, or General Inquiry). They also want to extract the customer's account number and order ID from each email. Which combination of Azure AI Language features should they use?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Text classification and custom entity recognition. The scenario requires two distinct NLP tasks: categorizing emails into predefined departments (Billing, Technical Support, General Inquiry) which is a text classification task, and extracting specific structured data (account number and order ID) which requires custom entity recognition to identify domain-specific entities not covered by prebuilt NER. Azure AI Language provides both custom text classification and custom entity recognition features to handle these requirements.

Answer

Sentiment analysis and key phrase extraction

Answer

Language detection and translation

Answer

Named entity recognition (NER) and summarization

Question 2

A healthcare clinic uses an AI system to triage patients by urgency. The system consistently assigns lower priority to patients presenting with rare symptoms compared to those with common symptoms, even when the rare symptoms indicate a serious condition. The clinic wants to ensure the system treats all patients equitably. According to Microsoft's Responsible AI principles, which principle is most directly relevant to addressing this disparity?

Accepted Answer

Fairness. The AI system's consistent assignment of lower priority to patients with rare symptoms, despite those symptoms indicating serious conditions, is a clear case of algorithmic bias that leads to unfair treatment outcomes. Microsoft's Fairness principle directly addresses this by requiring AI systems to allocate resources and make decisions without discrimination or favoritism, ensuring equitable treatment across all patient groups regardless of symptom prevalence.

Answer

Inclusiveness

Answer

Transparency

Answer

Accountability

Question 3

What is 'Azure OpenAI on your data' and what does it enable?

Accepted Answer

A managed RAG feature that answers questions from your connected data sources without custom pipeline code. 'Azure OpenAI on your data' is a managed Retrieval Augmented Generation (RAG) feature that allows you to connect Azure OpenAI models directly to your data sources (e.g., Azure Blob Storage, Azure Cosmos DB, or Azure AI Search) without writing custom orchestration code. It enables the model to ground its responses in your proprietary data, improving accuracy and relevance while reducing hallucinations.

Answer

Training a custom Azure OpenAI model exclusively on your proprietary data

Answer

Restricting Azure OpenAI to only use data from your Azure subscription, blocking external knowledge

Answer

A billing option that charges based on the volume of your data processed rather than tokens

Question 4

A retail company wants to automatically determine whether customer reviews are positive, negative, or neutral. Which prebuilt Azure AI Language feature should they use?

Accepted Answer

Sentiment analysis. Sentiment analysis is the correct Azure AI Language feature because it is specifically designed to classify text into positive, negative, or neutral sentiment categories. This prebuilt capability analyzes customer reviews at the document and sentence level, returning a sentiment label and confidence scores, which directly meets the requirement of automatically determining review polarity.

Answer

Key phrase extraction

Answer

Language detection

Answer

Entity recognition

Question 5

A developer is using Azure OpenAI to generate Python code snippets. They notice that the generated code often contains syntax errors because the model introduces too much randomness. Which parameter should the developer decrease to make the output more deterministic and reduce syntax errors?

Accepted Answer

Temperature. Temperature controls the randomness of the model's output. Lowering the temperature (e.g., from 1.0 to 0.2) reduces the probability of sampling less likely tokens, making the model more deterministic and less prone to generating syntactically incorrect code. By decreasing temperature, the developer forces the model to choose higher-probability tokens, which typically results in more predictable and syntactically valid Python code.

Answer

Top_p

Answer

Frequency_penalty

Answer

Max_tokens

Question 6

An autonomous drone delivery company uses an AI model to navigate. During testing in a new city, the model fails to detect power lines and crashes into them. The company wants to ensure their system is robust to unusual conditions. Which Microsoft responsible AI principle is most directly relevant?

Accepted Answer

Reliability and Safety. The scenario describes a failure in an AI system that leads to a physical safety hazard (crashing into power lines). The Microsoft responsible AI principle of Reliability and Safety directly addresses the need for AI systems to operate reliably under a range of conditions and to fail safely when they encounter unexpected situations. Ensuring robustness to unusual conditions, such as unseen power lines in a new city, is a core requirement of this principle.

Answer

Fairness

Answer

Privacy and Security

Answer

Inclusiveness

Question 7

What does Azure AI Vision's 'dense captioning' feature do?

Accepted Answer

Generates natural language descriptions for multiple regions within a single image. Azure AI Vision's dense captioning feature goes beyond generating a single caption for the entire image. It analyzes the image to identify multiple distinct regions (e.g., a person, a car, a building) and generates a natural language description for each region, along with bounding box coordinates. This is correct because the feature's core purpose is to provide granular, region-level descriptions, not just a single long caption.

Answer

Creates very long detailed captions for entire images

Answer

Extracts text from dense text-heavy images like documents

Answer

Analyzes the density of objects in an image for crowd counting

Question 8

A law firm needs to automatically process incoming legal documents. They have two specific requirements: (1) extract the names of all parties involved, the court name, and the filing date; (2) categorize each document as a 'complaint', 'motion', or 'subpoena'. Which two Azure AI Language features should they use? (Choose two.)

Accepted Answer

Custom text classification. Custom text classification (C) is correct because it allows the law firm to train a model to categorize legal documents into custom classes like 'complaint', 'motion', or 'subpoena' based on labeled examples. This feature is designed for domain-specific classification tasks where predefined categories are insufficient.

Answer

Sentiment analysis

Answer

Key phrase extraction

Question 9

What is 'k-fold cross-validation' specifically and how is k=10 different from k=5?

Accepted Answer

k=10 provides more reliable performance estimates at 2x the compute cost vs k=5. k-fold cross-validation splits the dataset into k equal folds, training on k-1 folds and validating on the remaining fold, repeating this process k times. With k=10, each model is trained on 90% of the data and validated on 10%, while k=5 uses 80% for training and 20% for validation. The key difference is that k=10 yields a performance estimate with lower variance (more reliable) because it averages over more folds, but it requires approximately twice the computational cost (10 training runs vs. 5).

Answer

k=10 always produces a better model than k=5 because it uses more training data

Answer

k=5 and k=10 produce identical results because the total data is the same

Answer

k=10 requires 10 times more labelled data than k=5

Question 10

A data scientist trains a binary classification model to detect fraudulent transactions. The dataset contains only 2% fraudulent transactions. The model achieves 98% overall accuracy, but it fails to detect any fraudulent transactions, classifying all transactions as legitimate. Which metric would most clearly reveal this failure?

Accepted Answer

Recall. Recall (also known as sensitivity or true positive rate) measures the proportion of actual positive cases (fraudulent transactions) that were correctly identified by the model. In this scenario, the model classifies all transactions as legitimate, so it detects zero fraudulent transactions, yielding a recall of 0%. Despite 98% overall accuracy, the recall metric clearly exposes the model's complete failure to identify any fraud.

Answer

Precision

Answer

F1 score

Answer

Specificity

Question 11

What is 'ensemble learning' in machine learning?

Accepted Answer

Combining predictions from multiple models to produce a better overall prediction. Ensemble learning improves predictive performance by combining the outputs of multiple individual models (e.g., decision trees, neural networks) to reduce variance, bias, or noise. This technique leverages the 'wisdom of the crowd' principle, where the aggregated prediction often outperforms any single model, as seen in methods like Random Forest (bagging) or Gradient Boosting (boosting).

Answer

Training a single very large model on an ensemble of diverse datasets

Answer

Using a musical ensemble to record training audio data

Answer

Deploying a model to multiple Azure regions simultaneously

Question 12

A developer is using Azure OpenAI Service to generate product descriptions from technical specifications. The generated descriptions sometimes include plausible-sounding but incorrect details (hallucinations). The developer wants to ensure the model's responses are strictly based on the provided product data and does not add any external or invented information. Which approach should the developer use?

Accepted Answer

Use Azure OpenAI On Your Data to connect to a product database so the model retrieves and references only the provided specifications.. Azure OpenAI On Your Data allows the developer to ground the model's responses in a specific data source, such as a product database. This ensures the model retrieves and references only the provided specifications, preventing the generation of external or invented information (hallucinations). By using this feature, the model's outputs are strictly based on the connected data, aligning with the requirement for factual accuracy.

Answer

Increase the frequency penalty to discourage the model from repeating common phrases.

Answer

Decrease the temperature to 0 so the model always picks the most likely next token, making it more predictable.

Answer

Enable content filtering to block any outputs that contain harmful or biased language.

Question 13

What is 'Azure Machine Learning workspace' and what does it contain?

Accepted Answer

The top-level Azure resource that organises all ML artefacts including models, experiments, and compute for a project. An Azure Machine Learning workspace is the top-level Azure resource that serves as a centralized hub for all machine learning activities. It contains essential artifacts such as datasets, experiments, models, pipelines, compute targets (e.g., compute clusters, inference clusters), and endpoints, enabling end-to-end ML lifecycle management within a single project.

Answer

A physical office space at Microsoft where ML engineers develop Azure AI services

Answer

A virtual desktop environment pre-configured with ML tools for data scientists

Answer

A shared document repository for storing ML project documentation and reports

Question 14

A hospital uses an AI system to analyze patient health records for research. The hospital must ensure that all patient data is stored securely and only authorized personnel can access it. Which Microsoft responsible AI principle is most directly relevant?

Accepted Answer

Privacy and security. The scenario explicitly focuses on secure storage and access control of patient data, which directly aligns with Microsoft's responsible AI principle of Privacy and security. This principle ensures that data is protected against unauthorized access and breaches, often implemented through encryption (e.g., AES-256 for data at rest, TLS 1.2+ for data in transit) and role-based access control (RBAC) in Azure services like Azure SQL Database or Azure Blob Storage.

Answer

Fairness

Answer

Transparency

Answer

Inclusiveness

Question 15

A market research firm wants to analyze thousands of customer reviews to automatically identify frequently mentioned product aspects and the sentiment associated with each aspect. For example, they want to know that 'battery life' is mentioned often with negative sentiment, while 'design' is mentioned with positive sentiment. Which Azure AI Language capability is best suited for this task?

Accepted Answer

Aspect-based Sentiment Analysis (Opinion Mining). Aspect-based Sentiment Analysis (Opinion Mining) is the correct choice because it goes beyond general sentiment to identify specific aspects (e.g., 'battery life', 'design') mentioned in text and the sentiment associated with each aspect. This directly matches the requirement to automatically detect frequently mentioned product aspects and their corresponding sentiments from customer reviews.

Answer

Key Phrase Extraction

Answer

Sentiment Analysis

Answer

Named Entity Recognition (NER)

Question 16

What is the 'inclusiveness' principle in Microsoft's responsible AI framework?

Accepted Answer

AI systems should be designed to benefit and empower all people, including marginalized groups. The 'inclusiveness' principle in Microsoft's responsible AI framework mandates that AI systems should be designed to benefit and empower all people, including marginalized groups. This ensures that AI solutions do not perpetuate bias or exclude underrepresented populations, aligning with Microsoft's commitment to fairness and accessibility in AI workloads.

Answer

AI systems should be available in all countries without restriction

Answer

AI systems should be open-source and freely available

Answer

AI systems should include all possible features regardless of relevance

Question 17

A legal firm needs to analyze thousands of contracts to extract key information such as party names, dates, and monetary amounts. They also need to identify if certain clauses (e.g., non-compete, termination rights) are present. Which combination of Azure AI Language features should they use?

Accepted Answer

Named Entity Recognition and Key Phrase Extraction. Named Entity Recognition (NER) extracts predefined entities such as person names, dates, and monetary amounts from text, which directly addresses the need to identify party names, dates, and monetary amounts in contracts. Key Phrase Extraction identifies the main points or topics in a document, making it suitable for detecting the presence of specific clauses like non-compete or termination rights by surfacing the key phrases that represent those clauses.

Answer

Entity Linking and Language Detection

Answer

Sentiment Analysis and Key Phrase Extraction

Answer

Text Analytics for Health and Entity Recognition

Question 18

What is 'text moderation' in Azure AI Content Safety for NLP workloads?

Accepted Answer

AI analysis of text for hate, violence, sexual, and self-harm content with per-category severity scores. Text moderation in Azure AI Content Safety uses trained NLP models to analyze text and assign severity scores (0-7) for four harm categories: hate, violence, sexual, and self-harm. This allows content filtering based on policy thresholds, not simple keyword matching. Option B correctly describes this AI-driven analysis with per-category severity scoring.

Answer

Grammatically correcting and editing text for quality before publishing

Answer

Moderating the volume of text content uploaded by users to prevent spam

Answer

Identifying and removing personally identifiable information from text before processing

Question 19

A hospital deploys an AI system that predicts patient readmission risk within 30 days of discharge. The model uses features such as age, medical history, and treatment plans. The hospital discovers that the model has a significantly higher false positive rate for patients of a certain ethnic group compared to others, even though the model's overall accuracy is similar across groups. This disparity was not intentional. Which Microsoft responsible AI principle is most directly compromised?

Accepted Answer

Fairness. The Fairness principle requires AI systems to treat all groups equitably and avoid discrimination. A higher false positive rate for one ethnic group, even if unintentional, represents an unfair disparity. While Inclusiveness relates to designing for all people, Fairness specifically addresses equitable outcomes and bias mitigation, so it is the most directly compromised principle in this case.

Answer

Reliability and safety

Answer

Privacy and security

Answer

Accountability

Question 20

What is fine-tuning in the context of large language models?

Accepted Answer

Training a pre-trained model further on domain-specific data to improve task performance. Fine-tuning takes a pre-trained large language model (LLM) and continues the training process on a smaller, domain-specific dataset. This adjusts the model's weights to specialize its outputs for particular tasks (e.g., legal document summarization or medical Q&A) without retraining from scratch. It is distinct from prompt engineering or retrieval-augmented generation because it permanently modifies the model parameters.

Answer

Adjusting the model's response speed for production deployment

Answer

Manually reviewing and correcting model outputs

Answer

Compressing a large model into a smaller, faster version