AI-102 Practice Test 14 — 15 Questions

Question 1

Your company uses Azure AI Language to analyze customer feedback. The solution currently uses the default endpoint and key. Security policy requires that all API calls be authenticated using Microsoft Entra ID and that network access be restricted to a specific virtual network. You need to reconfigure the resource. What should you do?

Accepted Answer

Disable local authentication, enable managed identity, and configure the virtual network. Option A is correct because it addresses both security requirements: disabling local authentication ensures that API keys cannot be used, forcing all calls to authenticate via Microsoft Entra ID; enabling a managed identity provides a secure identity for the resource to authenticate with Entra ID; and configuring the virtual network restricts network access to the specified VNet, meeting the network restriction policy.

Answer

Regenerate the API keys and update the application

Answer

Create a private endpoint for the resource

Answer

Configure the resource to use Microsoft Entra ID authentication only

Question 2

Your company uses Azure AI Search to power a customer-facing product catalog search. The search index contains product data from Azure SQL Database. The indexer runs daily. Lately, users complain that new products appear in the catalog with a delay of up to 24 hours. The business requires near real-time indexing (within minutes) for new products. You have the following constraints: - The indexer must continue to run daily for full sync. - You need to minimize changes to the existing architecture. - You cannot use Azure Functions or Logic Apps due to cost. What should you do?

Accepted Answer

Add a high-water mark change detection policy (e.g., based on a LastModified column) to the indexer data source. Set the indexer to run every 5 minutes.. Option D is correct. By creating a data change detection policy (e.g., using a LastModified timestamp), the indexer can track incremental changes. Setting the indexer schedule to run every 5 minutes allows near real-time updates. The daily full sync can still be run separately. Option A is wrong because the push API requires code changes and additional infrastructure (e.g., a service to push changes). Option B is wrong because Azure SQL Database change tracking is more complex and not necessary. Option C is wrong because removing the schedule would require manual runs, not solving the delay.

Answer

Enable change tracking on the Azure SQL Database and configure the indexer to use it.

Answer

Modify the application to use the push API to upload new products to the index as they are added.

Answer

Remove the daily indexer schedule and instead trigger the indexer manually after each new product insertion.

Question 3

Which TWO actions should you take to ensure high availability for an Azure AI service deployed in a single region?

Accepted Answer

Configure autoscaling for the AI service.. Option A is correct because autoscaling allows the Azure AI service to dynamically adjust the number of instances based on demand, ensuring that the service can handle traffic spikes without downtime. This is a key high-availability feature within a single region, as it prevents resource exhaustion and maintains responsiveness. Option C is correct because deploying the AI service in a second Azure region provides geographic redundancy, enabling failover if the primary region experiences an outage, which is a fundamental high-availability strategy.

Answer

Use a read-only replica of the AI service.

Answer

Enable Azure DDoS Protection.

Answer

Enable Azure Backup for the AI resource.

Question 4

Your company is developing an AI-powered document processing solution using Azure AI Document Intelligence. The solution must extract data from scanned PDF forms. The forms are in a custom format not supported by prebuilt models. You have 10,000 labeled forms for training. The solution must be deployed in a region that supports Document Intelligence and must be accessible via a REST API. You need to ensure the solution can process forms with high accuracy. What should you do?

Accepted Answer

Train a custom extraction model using the labeled forms. Option B is correct because Azure AI Document Intelligence supports training custom extraction models using labeled forms, which is essential for handling custom form layouts not covered by prebuilt models. With 10,000 labeled forms, you have sufficient data to train a high-accuracy model that extracts specific fields via the REST API, meeting the deployment and accessibility requirements.

Answer

Use Azure AI Language to extract entities from the text

Answer

Use a prebuilt model and map fields manually

Answer

Use the Read model and write custom logic to extract fields

Question 5

You are designing a solution that uses Azure AI Language to analyze customer feedback. The solution must detect sentiment, extract key phrases, and identify named entities. Which feature should you use?

Accepted Answer

Azure AI Language service. The Azure AI Language service provides pre-built capabilities for sentiment analysis, key phrase extraction, and named entity recognition (NER) as part of its text analytics features. These three tasks are directly supported by the service's Analyze API, making it the correct choice for analyzing customer feedback text.

Answer

Azure AI Speech service

Answer

Azure AI Computer Vision

Answer

Translator API

Question 6

You are developing an Azure AI solution that uses pre-built models from Azure AI Vision to analyze images. The solution must be able to detect objects and read printed text. Which TWO capabilities should you use?

Accepted Answer

Object detection. Option C is correct because Azure AI Vision's Object Detection capability identifies and locates objects within an image, returning bounding box coordinates and labels. This directly meets the requirement to 'detect objects' in the solution.

Answer

OCR (legacy)

Answer

Facial detection

Answer

Image tagging

Question 7

You are planning to use Azure AI Document Intelligence to process a large volume of mixed document types (invoices, receipts, and purchase orders). The solution must automatically classify each document type and extract relevant fields. What should you configure?

Accepted Answer

Create a custom classification model to identify document types, then use extraction models. Option B is correct because Azure AI Document Intelligence (formerly Form Recognizer) requires a two-step process for mixed document types: first, a custom classification model identifies each document type (invoice, receipt, purchase order), then separate extraction models (custom or prebuilt) extract the relevant fields from each classified type. This approach ensures accurate routing and field extraction without relying on filenames or brittle regex patterns.

Answer

Use the Form Recognizer service with neural models

Answer

Use prebuilt models for each document type and route based on filename

Answer

Use the Read model to extract all text and then use regular expressions to classify

Question 8

You are planning an Azure AI solution that uses Azure AI Search with semantic ranker and a custom skill. The solution must meet the following requirements: - Process documents in multiple languages (English, Spanish, French). - Use a custom skill to extract entities via an Azure Function. - Ensure that the indexer can resume from failures. Which TWO actions should you include in your plan?

Accepted Answer

Generate a data change detection policy on the data source.. Option A is correct because a data change detection policy (e.g., HighWaterMarkChangeDetectionPolicy or SqlIntegratedChangeTrackingPolicy) enables the indexer to track which documents have been modified or added. This allows the indexer to resume from failures by reprocessing only the changed or unprocessed documents, rather than starting over from scratch. Without this policy, a failure would require a full reindex, which is inefficient and violates the requirement to resume from failures.

Answer

Configure separate indexer data sources for each language.

Answer

Set the indexer property 'maxFailedItems' to a high value.

Answer

Enable Azure Monitor logs for the indexer to track failures.

Question 9

Refer to the exhibit. You are implementing an Azure AI Search index for semantic search with vector support. The index includes a field 'descriptionVector' of type Collection(Edm.Single) with 1536 dimensions. When you run a vector search query, you notice that results are not sorted by relevance. What is the most likely cause?

Accepted Answer

The index does not have a vector configuration with a similarity metric. Option C is correct because Azure AI Search requires a vector configuration with a similarity metric (e.g., cosine, dotProduct, euclidean) to compute relevance scores for vector search results. Without this configuration, the search engine cannot sort results by relevance, leading to unsorted or default ordering. The similarity metric is defined in the index's vector configuration and is essential for ranking vector query results.

Answer

The 'descriptionVector' field is not searchable

Answer

The vector dimensions do not match the embedding model output

Answer

The 'descriptionVector' field is set as retrievable: false

Question 10

Your company is deploying an Azure AI Document Intelligence solution to process invoices. The solution must: - Extract key fields (invoice number, date, total amount). - Handle invoices in both PDF and image formats. - Use a prebuilt model to reduce development effort. - Process high volumes (up to 10,000 invoices per day). - Store extracted data in Azure Cosmos DB. You need to design the processing pipeline. What should you do?

Accepted Answer

Use the prebuilt invoice model with the async API. Submit all invoices for analysis. Use an Azure Function to poll for results and write to Cosmos DB.. Option B is correct because the prebuilt invoice model's asynchronous API is designed for high-volume batch processing, allowing you to submit up to 10,000 invoices per day without timeout or rate-limit issues. The async API returns operation locations that you can poll via an Azure Function, and once results are ready, you write the extracted fields (invoice number, date, total amount) to Azure Cosmos DB. This decouples submission from retrieval, ensuring scalability and reliability for both PDF and image formats.

Answer

Use the synchronous API of the prebuilt invoice model. For each invoice, call the API and write the result to Cosmos DB.

Answer

Use the prebuilt receipt model to process invoices. Store results in Cosmos DB.

Answer

Use the layout model to extract text from invoices. Then use Azure AI Language to extract entities.

Question 11

You need to generate a summary of a long article using Azure OpenAI. The article is 10,000 tokens long. What should you do to fit the article within the model's context window?

Accepted Answer

Split the article into smaller sections and summarize each section separately.. Option A is correct because the article exceeds the model's context window (typically 4096 or 8192 tokens for GPT-3.5/4). Splitting the article into smaller sections and summarizing each separately allows you to process the entire content within the token limits, then combine the summaries for a final coherent output. This is a standard chunking strategy for long documents when using Azure OpenAI.

Answer

Increase the temperature parameter.

Answer

Use a model with a smaller context window.

Answer

Set max_tokens to a lower value.

Question 12

A company uses Microsoft Copilot for Microsoft 365 to automate email responses. They want to ensure that the Copilot responses comply with their data governance policies and do not expose sensitive information. What should they configure?

Accepted Answer

Microsoft Purview Data Loss Prevention (DLP) policies. Microsoft Purview Data Loss Prevention (DLP) policies are designed to detect and prevent the accidental sharing of sensitive information, such as credit card numbers or personally identifiable information (PII), across Microsoft 365 services. By configuring DLP policies, the company can scan Copilot-generated email responses for sensitive data patterns and block or warn before the email is sent, ensuring compliance with data governance policies.

Answer

Microsoft Entra ID conditional access policies

Answer

Microsoft Intune app protection policies

Answer

Microsoft Sentinel analytics rules

Question 13

You need to create a chatbot that uses Azure OpenAI to answer questions about your company's internal policies. The responses must be based only on the provided policy documents. Which approach should you use?

Accepted Answer

Use Retrieval-Augmented Generation (RAG) with an Azure AI Search index of the documents.. Option B is correct because RAG uses provided documents as source. Option A is wrong because fine-tuning on policies may still generate ungrounded responses. Option C is wrong because prompt engineering alone does not enforce grounding. Option D is wrong because the model's training data is generic.

Answer

Use the model's pre-existing knowledge about common policies.

Answer

Fine-tune a GPT model on the policy documents.

Answer

Use prompt engineering to instruct the model to only use policy knowledge.

Question 14

You need to translate a document from English to Spanish using Azure OpenAI. Which parameter should you include in the prompt to specify the target language?

Accepted Answer

user message. To specify the target language in an Azure OpenAI translation prompt, you include the instruction within the user message (e.g., 'Translate the following English text to Spanish: ...'). The user message is the primary input where the model receives the task and context, making it the correct parameter for language specification.

Answer

max_tokens

Answer

temperature

Answer

system message

Question 15

You are designing a generative AI solution that uses Azure OpenAI GPT-4 to answer customer support questions. The solution must comply with Microsoft's Responsible AI principles, particularly transparency and accountability. Which implementation approach best meets these requirements?

Accepted Answer

Enable content filtering, log all interactions, and include a disclaimer that responses are AI-generated.. Option C is correct because it directly addresses Microsoft's Responsible AI principles of transparency and accountability. Enabling content filtering (via Azure AI Content Safety) ensures harmful outputs are blocked, logging all interactions provides an audit trail for accountability, and including a disclaimer that responses are AI-generated satisfies transparency by clearly informing users they are interacting with an AI system.

Answer

Use the model without any modifications, and have a human review all responses.

Answer

Fine-tune the model on a curated dataset of support tickets and disable content filtering.

Answer

Use the default model deployment and rely on the model's inherent safety.