AI-102 Practice Test 20 — 15 Questions

Question 1

You are a solution architect at a media company. The company uses Azure AI Speech to generate subtitles for videos. The current solution uses the batch transcription API and takes several hours to process a 1-hour video. The business requires near-real-time subtitles for live streaming events. You need to design a new solution that provides low-latency transcription. You have the following options:

Option A: Use the batch transcription API with a higher priority queue.

Option B: Use the Speech-to-text REST API for real-time streaming with the Speech SDK.

Option C: Use the Azure AI Language API to transcribe audio from a file.

Option D: Use Azure AI Video Indexer to generate subtitles.

Accepted Answer

Option B. The Speech-to-text REST API with the Speech SDK supports real-time streaming transcription, which provides low-latency results suitable for live streaming events. Unlike the batch transcription API, which processes audio asynchronously and can take hours, the streaming API processes audio chunks in near-real-time, returning partial and final results with sub-second latency.

Answer

Option C

Answer

Option D

Answer

Option A

Question 2

You are building a solution that uses Azure AI Language to analyze customer support transcripts. You need to detect personally identifiable information (PII) and also redact the detected PII from the text. Which TWO features should you use? (Select TWO.)

Accepted Answer

PII detection. PII detection (Option A) is correct because it is the Azure AI Language feature specifically designed to identify categories of personally identifiable information such as names, addresses, phone numbers, and social security numbers within text. PII redaction (Option D) is correct because it is the companion feature that replaces the detected PII entities with placeholder tokens (e.g., '********') or masks them, enabling safe sharing of transcripts. Together, they fulfill the requirement to both detect and redact PII from customer support transcripts.

Answer

Translation

Answer

Sentiment analysis

Answer

Key phrase extraction

Question 3

You are building an agent in Microsoft Copilot Studio that needs to send a confirmation email after a user completes a survey. The email should be sent using the user's email address collected during the conversation. Which feature should you use to send the email?

Accepted Answer

Create a Power Automate flow that sends an email and call it from the topic.. Microsoft Copilot Studio does not have a native 'Send an email' action; it relies on Power Automate flows to perform external actions like sending emails. By creating a flow that uses the user's email address collected during the conversation and calling it from the topic, you can send a confirmation email after the survey is completed.

Answer

Use the Send an email action directly in Copilot Studio.

Answer

Use an adaptive card with an email button.

Answer

Use the email channel to send a response.

Question 4

You run the PowerShell script above to call the Text Analytics API. The response shows a sentiment label of 'positive' with a score of 0.99. However, you expected 'negative' because the word 'excellent' was meant to be sarcastic. What is the most likely reason for this result?

Accepted Answer

The model does not detect sarcasm and interprets the text literally.. The Text Analytics API performs sentiment analysis using a machine learning model that evaluates the literal wording of the text. It does not have built-in capability to detect sarcasm, irony, or implied meaning. Therefore, the word 'excellent' is interpreted as positive regardless of the intended sarcastic tone, resulting in a high positive score.

Answer

The score threshold for negative sentiment is too high.

Answer

The language parameter is set incorrectly.

Answer

The API version does not support sentiment analysis.

Question 5

You need to extract key-value pairs from a large set of invoices. The invoices have a consistent layout but vary in format (PDF, TIFF). Which Document Intelligence model should you use?

Accepted Answer

Premade invoice model. The premade invoice model (D) is specifically designed to extract key-value pairs from invoices, including fields like invoice date, total amount, and vendor details, even when the invoices vary in format (PDF, TIFF). It leverages pre-trained deep learning models optimized for invoice layouts, making it the most efficient choice for this task without requiring custom training.

Answer

Custom extraction model

Answer

Layout model

Answer

Read model

Question 6

A manufacturing company uses Azure AI Custom Vision to detect defects on a production line. The model was trained with 500 images per class and achieves 95% accuracy. After deployment, the model's accuracy drops to 80% due to changes in lighting conditions. What is the most effective first step to improve the model's robustness?

Accepted Answer

Capture additional images under the new lighting and retrain the model.. The drop in accuracy is caused by a domain shift—specifically, new lighting conditions that were not represented in the original training set. The most effective first step is to capture additional images under the new lighting and retrain the model, as Custom Vision relies on diverse, representative training data to generalize to real-world variations. This directly addresses the root cause by expanding the training distribution to include the new lighting scenario, which is a fundamental principle of supervised learning in computer vision.

Answer

Reduce the probability threshold to increase recall.

Answer

Use Azure AutoML to automatically find the best algorithm.

Answer

Add more images from the original lighting conditions to the training set.

Question 7

You are building a knowledge mining solution for legal documents stored in Azure Blob Storage. The solution must extract entities, key phrases, and relationships from the documents. Which Azure AI service should you use?

Accepted Answer

Azure AI Language. Azure AI Language provides pre-built capabilities for entity extraction, key phrase extraction, and relationship extraction from text. This service includes features like Named Entity Recognition (NER), key phrase extraction, and document analysis that directly meet the requirements for extracting entities, key phrases, and relationships from legal documents. The other options lack one or more of these specific text analytics capabilities.

Answer

Azure AI Document Intelligence

Answer

Azure AI Translator

Answer

Azure AI Search

Question 8

You are using Microsoft Purview to create a knowledge map of your organization's data assets. The solution must automatically scan and classify sensitive data in Azure Blob Storage. You need to configure the scanning and classification. Which THREE actions should you perform?

Accepted Answer

Run a full scan of the Blob Storage to discover and classify data.. Running a full scan of Azure Blob Storage in Microsoft Purview is the mechanism that discovers and classifies sensitive data. A full scan examines all files and metadata, applying the configured classification rules to identify sensitive information types such as credit card numbers or social security numbers. This action is essential for populating the knowledge map with classified data assets.

Answer

Create custom classification rules for sensitive data types.

Answer

Apply sensitivity labels to the classified data.

Question 9

Your company uses Azure AI Search for an internal knowledge base. Users complain that searches for 'annual report 2023' return irrelevant results. You analyze the search index and find that the content field contains large blocks of text from PDFs. You need to improve relevance without re-indexing all documents. Which approach should you take?

Accepted Answer

Enable semantic ranking on the search index. Semantic ranking re-ranks search results using deep learning models to understand the intent and context of the query, rather than just keyword matching. Since the content field contains large text blocks from PDFs, semantic ranking can extract the most relevant passages and improve result relevance without requiring re-indexing or modifying the existing index schema.

Answer

Enable spell correction in the search query

Answer

Add a custom scoring profile based on term frequency

Answer

Change the index analyzer to a different language

Question 10

Which TWO features of Azure AI Search allow you to improve the relevance of search results for users?

Accepted Answer

Semantic search. Semantic search (B) improves relevance by using deep neural networks to understand the intent and context behind a query, re-ranking results based on semantic relevance rather than just keyword matching. This allows users to find more meaningful results even when their query doesn't exactly match indexed terms.

Answer

Synonym maps

Answer

Suggesters

Answer

Filterable fields

Question 11

Your organization has a large corpus of legal documents stored in Azure Blob Storage. You need to build a solution that allows lawyers to ask natural language questions and get answers directly from the documents, without moving data out of Azure. Which service should you use?

Accepted Answer

Azure AI Search with semantic search. Azure AI Search with semantic search is the correct choice because it allows you to index legal documents stored in Azure Blob Storage, then query them using natural language questions. The semantic search capability re-ranks results based on contextual understanding, enabling the system to extract precise answers from the document corpus without moving data out of Azure.

Answer

Azure AI Document Intelligence

Answer

Azure AI Language Service with custom question answering

Answer

Azure AI Computer Vision

Question 12

You have the above data source definition for Azure AI Search. You want to index only PDF files from the 'documents' container. How should you modify the data source?

Accepted Answer

Set the 'query' field to a blob prefix that corresponds to the folder containing PDF files.. Azure AI Search data sources support a 'query' property that accepts a blob prefix or virtual directory path. By setting 'query' to the folder path containing PDFs (e.g., 'documents/pdfs/'), the indexer will only process blobs under that prefix, effectively filtering to PDF files without moving or renaming containers.

Answer

Change the container name to 'pdfs' and move all PDFs there.

Answer

Add a 'fileExtension' property to the container object.

Answer

Change the connection string to use a different storage account that contains only PDFs.

Question 13

Refer to the exhibit. A developer is testing the Text Analytics sentiment analysis API and receives a 401 error. What is the most likely cause?

Accepted Answer

The subscription key is invalid or expired.. The curl command uses 'wrongkey' instead of one of the valid keys shown in the output.

Answer

The API version is not supported.

Answer

The endpoint URL is incorrect.

Answer

The resource group is misspelled.

Question 14

Which THREE conditions must be met for Azure AI Search to use a custom skill? (Select THREE.)

Accepted Answer

The custom skill must handle batch requests of up to 1000 records per call.. Azure AI Search custom skills must be capable of processing batch requests containing up to 1000 records per call. This requirement ensures efficient indexing by allowing the search service to send multiple documents in a single HTTP request, reducing latency and overhead. The skill's endpoint must accept and return an array of records, with each record processed independently.

Answer

The custom skill must be stateless.

Answer

The custom skill must be hosted in an Azure Function.

Question 15

Your organization uses Azure AI Search to index customer product reviews. The reviews are in English, Spanish, and French. You need to enable multi-lingual search so that a query in English returns relevant results from all three languages. What should you do?

Accepted Answer

Create separate search fields for each language, each with the corresponding language analyzer (e.g., 'en.microsoft', 'es.microsoft', 'fr.microsoft').. Azure AI Search supports language-specific analyzers (e.g., 'en.microsoft', 'es.microsoft', 'fr.microsoft') that apply linguistic rules like stemming, lemmatization, and stop-word removal tailored to each language. By creating separate search fields with the corresponding analyzer, a query in English can match relevant terms across all three languages because the search engine evaluates the query against each field using its analyzer, allowing cross-language retrieval without translation.

Answer

Use Azure AI Translator to translate all reviews to English before indexing.

Answer

Use a single field with the 'standard' analyzer for all languages.

Answer

Use the 'keyword' analyzer for all fields.