AI-102 Practice Test 10 — 10 Questions

Question 1

You are deploying an Azure OpenAI model for a healthcare application. You need to ensure that the model does not generate medical advice and that all responses include a disclaimer. Which configuration should you use?

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

Accepted Answer

Configure a system message with instructions and enable content filtering.. Configuring a system message with explicit instructions (e.g., 'Do not provide medical advice; always include a disclaimer') combined with Azure AI Content Safety's content filtering allows you to enforce behavioral guardrails and block harmful outputs at the application layer. The system message sets the model's behavior, while content filtering provides a secondary safety net to catch policy violations, ensuring compliance in a regulated healthcare environment.

Answer

Ground the model with your own medical documents.

Answer

Set max_tokens to 50 to limit response length.

Answer

Use Azure AI Content Safety to filter medical terms.

Question 2

A news organization wants to automatically summarize long articles into short, coherent summaries. The solution must preserve the original meaning and key points. Which Azure AI service should be used?

Accepted Answer

Azure AI Language - Extractive Summarization. Azure AI Language's Extractive Summarization is specifically designed to generate concise summaries by extracting the most important sentences from a document while preserving the original meaning and key points. This service uses natural language processing to rank sentences based on relevance and coherence, making it ideal for summarizing long articles without altering the original content.

Answer

Azure AI Document Intelligence

Answer

Azure AI Language - Key Phrase Extraction

Answer

Azure AI Translator

Question 3

You are deploying a generative AI application that uses Azure OpenAI Service. You need to ensure that the application can handle sudden spikes in traffic without exceeding your quota. Which scaling strategy should you implement?

Accepted Answer

Configure a provisioned throughput deployment with auto-scaling.. Provisioned throughput (PTU) deployments with auto-scaling are designed to handle sudden traffic spikes by automatically adjusting capacity within your configured limits, ensuring consistent performance without exceeding quota. This approach provides reserved throughput that can scale up during demand surges and scale down when traffic subsides, unlike pay-as-you-go which is subject to global rate limits and may throttle during spikes.

Answer

Use a Pay-as-you-go deployment and rely on Azure's automatic scaling.

Answer

Create a deployment with a high base TPM and manually adjust during peak times.

Answer

Deploy multiple instances of the model in different regions.

Question 4

You are responsible for ensuring that an Azure AI solution complies with data residency requirements. The solution processes personal data from users in the European Union. You must ensure that data does not leave the EU region. Which two actions should you take?

Accepted Answer

Configure the Azure AI services to disable cross-region replication.. Disabling cross-region replication ensures that data processed by Azure AI services remains within the specified region and is not automatically replicated to another geographic location for redundancy or disaster recovery. This is a critical control for meeting data residency requirements, as it prevents data from leaving the EU region even during failover scenarios.

Answer

Use the global Azure AI services endpoint for simplicity.

Answer

Enable data encryption at rest and in transit.

Answer

Store data in Azure Blob Storage with hot tier.

Question 5

You deploy a custom vision model using Azure AI Custom Vision. After deployment, you notice the model has high accuracy on training data but low accuracy on new images. What is the most likely cause?

Accepted Answer

The model is overfitted to the training data. High accuracy on training data but low accuracy on new images is the classic symptom of overfitting, where the model has memorized the training examples (including noise and irrelevant patterns) rather than learning generalizable features. In Azure AI Custom Vision, this typically occurs when the training dataset is too small, too homogeneous, or lacks sufficient variation, causing the model to fail on unseen data.

Answer

The training time was too short

Answer

The training dataset has too few images

Answer

The wrong domain was selected during training

Question 6

Refer to the exhibit. You are configuring an Azure OpenAI Service deployment for document summarization. The current parameters produce summaries that are often too verbose. You need to make the summaries more concise while maintaining factual accuracy. Which parameter change should you make?

Accepted Answer

Decrease max_tokens to 100. Decreasing max_tokens to 100 directly limits the maximum length of the generated summary, forcing the model to produce shorter output. This addresses the verbosity issue without altering the model's factual accuracy, as max_tokens controls output length, not content selection or creativity.

Answer

Increase top_p to 1.0

Answer

Increase frequency_penalty to 0.5

Answer

Increase temperature to 0.7

Question 7

Your organization is using Azure AI Search to index a large collection of PDF documents stored in Azure Blob Storage. The index currently returns search results, but users complain that the results are not relevant when they search using natural language phrases. You need to improve the relevance of search results without rewriting the application. What should you do?

Accepted Answer

Enable semantic search on the index and configure a semantic configuration.. Semantic search in Azure AI Search uses advanced language models to understand the intent behind natural language queries, re-ranking results based on semantic relevance rather than just keyword matching. Enabling semantic search and configuring a semantic configuration directly addresses the user complaint about poor relevance for natural language phrases without requiring application changes.

Answer

Increase the number of replicas for the search service to improve query performance.

Answer

Create a new index with a blob indexer that uses the 'content' field only.

Answer

Configure a custom analyzer on the index to handle stop words and synonyms.

Question 8

You are designing a solution that uses Azure AI Document Intelligence to extract data from invoices. The solution must classify invoices by vendor and extract line items. Which prebuilt model should you use?

Accepted Answer

Prebuilt invoice model. The Prebuilt invoice model (Option A) is specifically designed to extract common fields from invoices, including vendor details and line items, without requiring custom training. This model is optimized for invoice documents and provides out-of-the-box extraction of structured data such as vendor name, invoice date, and line-item descriptions, quantities, and amounts.

Answer

Custom extraction model

Answer

Prebuilt receipt model

Answer

Prebuilt layout model

Question 9

Which TWO actions should you take when designing an Azure AI solution that uses Microsoft Foundry to ensure responsible AI practices?

Accepted Answer

Implement a human-in-the-loop review for critical decisions. Implementing a human-in-the-loop review provides oversight for critical decisions. Option C is correct because running an AI fairness assessment detects bias. Option B is wrong because optimizing for maximum throughput is about performance, not responsible AI. Option D is wrong because storing all training data indefinitely may violate privacy and is not a recommended practice for responsible AI. Option E is wrong because removing all explainability metrics hinders transparency, which is important for responsible AI.

Answer

Optimize the model for maximum throughput

Answer

Store all training data indefinitely for auditability

Answer

Remove all explainability metrics to simplify the model

Question 10

A company is planning to use Azure AI services. They require the ability to audit all API calls for compliance. Which THREE components should they enable?

Accepted Answer

Azure Monitor. Azure Monitor is correct because it provides a centralized platform for collecting, analyzing, and acting on telemetry data from Azure resources, including API call logs. By enabling diagnostic settings for the AI service, you can route audit logs (such as all REST API requests and responses) to Azure Monitor, which then integrates with Log Analytics for querying and alerting. This triad—Azure Monitor, Log Analytics workspace, and diagnostic settings—forms the complete pipeline required to audit all API calls for compliance.

Answer

Azure RBAC roles for the service

Answer

Managed identity for the service