AI-102 Practice Test 29 — 15 Questions

Question 1

Match each Azure AI pricing tier to its description.

Accepted Answer

Free (F0): Provides limited transactions per month at no cost.. Common Azure Cognitive Services pricing tiers include Free (limited free transactions), Standard S0 (pay-as-you-go moderate), and Premium (enterprise high-throughput).

Answer

Free (F0): Pay-as-you-go pricing for moderate workloads.

Answer

Standard (S0): Designed for high-scale enterprise workloads with higher throughput.

Answer

Premium: Provides limited transactions per month at no cost.

Question 2

You need to monitor costs for an Azure AI solution that uses multiple Azure AI services. Which Azure tool should you use to set budgets and receive alerts?

Accepted Answer

Azure Cost Management. Azure Cost Management is the dedicated Azure tool for setting budgets, defining cost thresholds, and configuring alerts when spending exceeds those limits. It provides detailed cost analysis, forecasting, and policy enforcement across all Azure services, including AI services like Cognitive Services and Azure Machine Learning.

Answer

Azure Advisor

Answer

Azure Monitor

Answer

Azure Service Health

Question 3

You are tasked with creating a solution that can identify and count people in a retail store to analyze foot traffic. Which TWO Azure AI services can be used together?

Accepted Answer

Azure AI Video Indexer. Azure AI Video Indexer can extract insights from video feeds, including detecting and counting people in a retail store by analyzing recorded or live video streams. Azure AI Vision Spatial Analysis provides real-time computer vision capabilities specifically designed for counting people and measuring foot traffic in physical spaces, such as retail environments. Together, these services enable both historical analysis (Video Indexer) and real-time monitoring (Spatial Analysis) of people flow.

Answer

Azure AI Content Safety

Answer

Azure AI Document Intelligence

Answer

Azure AI Face

Question 4

You are designing an agent that uses Azure AI Search as a knowledge store. The agent must handle multiple languages. Which feature should you configure in Azure AI Search to ensure the agent retrieves relevant results for queries in different languages?

Accepted Answer

Language analyzers. Language analyzers in Azure AI Search are specifically designed to handle linguistic variations across different languages, such as stemming, stop word removal, and tokenization rules. By configuring the appropriate language analyzer (e.g., 'en.microsoft' for English or 'fr.microsoft' for French) on a searchable field, the agent can retrieve relevant results for queries in multiple languages because the analyzer processes both the indexed content and the query string using the same language-specific rules.

Answer

Scoring profiles

Answer

Semantic search

Answer

Synonym maps

Question 5

Your team has built a knowledge mining pipeline using Azure AI Search and Document Intelligence. After ingestion, you notice that some documents are not appearing in search results. What is the most likely cause?

Accepted Answer

The indexer encountered errors and marked the documents as failed. If the indexer encounters errors while processing specific documents (e.g., unsupported formats, parsing failures, or skill errors), those documents are marked as failed and not indexed. This explains why only some documents are missing from search results. Option B is incorrect because semantic configuration affects ranking and relevance features, not whether documents are indexed. Option C is incorrect because insufficient replicas affect query performance and availability, not document ingestion. Option D is incorrect because throttling during high query volume would impact all search queries, not the indexing of specific documents.

Answer

The index does not have a semantic configuration

Answer

The search service has insufficient replicas

Answer

The search service is throttled due to high query volume

Question 6

A company is using Azure AI Vision to analyze images from a manufacturing line. The solution must detect defects in real-time. The team discovers that the model's accuracy drops significantly when images are captured under different lighting conditions. What is the best approach to improve the model's robustness?

Accepted Answer

Retrain the model using images captured under various lighting conditions, using data augmentation.. Retraining the model with images captured under various lighting conditions, along with data augmentation, directly exposes the model to diverse lighting scenarios, improving its robustness. Option A is incorrect because while image pre-processing can help normalize lighting, it may not fully compensate for the lack of varied training data, and the model may still not generalize well to unseen lighting conditions. Option B is incorrect because simply increasing the number of training images without varying lighting conditions does not help the model learn to handle different lighting; it only reinforces the existing bias. Option D is incorrect because using a pre-built model from Azure AI Vision may not be tailored for the specific defect detection task and may still suffer from sensitivity to lighting changes without retraining.

Answer

Apply image pre-processing to normalize lighting before sending to the model.

Answer

Increase the number of training images without varying lighting conditions.

Answer

Use a pre-built model from Azure AI Vision instead of a custom model.

Question 7

Your organization uses Azure AI Language to analyze customer support tickets. You need to ensure that personally identifiable information (PII) is detected and redacted before further processing. Which TWO features should you use?

Accepted Answer

Redaction. Redaction (Option B) is correct because it is the process of masking or removing detected PII from text, which directly meets the requirement to ensure PII is redacted before further processing. Azure AI Language provides a dedicated PII detection and redaction feature that identifies categories such as names, phone numbers, and credit card numbers, and then replaces them with placeholders like '********' or entity type labels.

Answer

Entity linking

Answer

Conversation summarization

Answer

Key phrase extraction

Question 8

Refer to the exhibit. You send this request to the Azure AI Language Service for custom entity recognition. The response returns no entities. What is the most likely reason?

Accepted Answer

The projectName and deploymentName are missing from the body parameters. The Azure AI Language Service for custom entity recognition requires both `projectName` and `deploymentName` in the request body to identify which trained custom model to invoke. Without these parameters, the service cannot route the request to the correct custom model, so it returns no entities. The standard pre-built entity recognition does not require these fields, but custom entity recognition mandates them.

Answer

The text input is too short for entity recognition

Answer

The language parameter is set incorrectly

Answer

The model version is not specified

Question 9

You are architecting an Azure AI solution that uses Azure AI Language to analyze text for sentiment and key phrases. The solution must handle bursts of up to 500 requests per second but average only 50 requests per second. You need to ensure cost efficiency while meeting performance requirements. Which THREE actions should you take?

Accepted Answer

Use Azure Queue Storage to buffer requests during spikes. Azure Queue Storage can decouple the ingestion of requests from processing, allowing the solution to buffer bursts of up to 500 requests per second while the Azure AI Language service processes at a lower sustained rate. This prevents request throttling and enables cost-efficient scaling by using a lower-cost queue to absorb spikes rather than over-provisioning the AI service tier.

Answer

Select the Free tier and implement queuing

Answer

Deploy the service in multiple regions

Question 10

You are designing an AI solution that uses Azure AI Document Intelligence to extract data from invoices. The solution must handle a high volume of documents with varying layouts. Which approach should you use?

Accepted Answer

Train a custom neural model with labeled invoices. Custom neural models in Azure AI Document Intelligence are designed to handle high volumes of documents with varying layouts. Unlike fixed template models, neural models learn from labeled examples and generalize across different invoice structures, making them ideal for diverse, high-volume scenarios.

Answer

Use a custom template model with fixed field positions

Answer

Use the prebuilt invoice model

Answer

Extract text using OCR and then use regex parsing

Question 11

Which THREE components are required to build a custom named entity recognition (NER) model in Azure Cognitive Service for Language?

Accepted Answer

A set of labeled documents for training.. A custom NER model in Azure Cognitive Service for Language requires a set of labeled documents for training. These labeled documents define the entities and their spans within text, which the model uses to learn patterns for extraction. Without labeled data, the model cannot be trained to recognize custom entities.

Answer

A QnA Maker knowledge base for entity definitions.

Answer

A LUIS application to handle entity extraction.

Question 12

Your team is building a knowledge mining solution for research papers. You need to automatically categorize papers into topics and extract author names, publication dates, and references. The solution must use custom models because the papers are domain-specific. Which combination of Azure services should you use?

Accepted Answer

Azure AI Document Intelligence's custom extraction model and Azure AI Language's custom text classification. It combines Azure AI Document Intelligence's custom extraction model to extract domain-specific fields like author names, publication dates, and references, with Azure AI Language's custom text classification to categorize research papers into topics. This pairing directly addresses the need for custom models tailored to the specialized domain, unlike pre-built or generic solutions.

Answer

Azure AI Document Intelligence's pre-built invoice model and Azure Bot Service

Answer

Azure AI Search's built-in OCR skill and a custom skill using Azure Functions

Answer

Azure AI Language's pre-built entity extraction and Azure AI Search

Question 13

You need to generate a poem using Azure OpenAI. The poem should be about nature and have a cheerful tone. Which parameter should you adjust to influence the tone?

Accepted Answer

system message. The system message is the correct parameter to influence the tone of the generated poem because it sets the initial context, persona, and behavioral guidelines for the model. By including an instruction like 'You are a cheerful poet who writes about nature in a happy tone,' you directly control the style and emotional quality of the output, which is exactly what the question requires.

Answer

max_tokens

Answer

top_p

Answer

temperature

Question 14

You need to provide a generative AI solution that can answer questions based on a large set of PDF documents stored in Azure Blob Storage. The solution must support natural language queries and return citations from the documents. Which Azure service combination should you use?

Accepted Answer

Azure Cognitive Search and Azure OpenAI Service with 'on your data'. Azure Cognitive Search provides the indexing and retrieval capabilities for the PDF content, while Azure OpenAI Service with the 'on your data' feature enables natural language querying and generates answers grounded in the indexed documents, including citations. This combination directly supports the requirement to query a large set of PDFs in Azure Blob Storage and return citations.

Answer

Azure Machine Learning and Azure Kubernetes Service

Answer

Azure AI Bot Service and Azure Functions

Answer

Azure AI Document Intelligence and Azure AI Translator

Question 15

Your organization uses Azure AI Vision to analyze surveillance images for security threats. The solution must comply with GDPR. Which TWO actions should you take?

Accepted Answer

Disable logging of request and response data.. Disabling logging of request and response data is a direct measure to minimize personal data processing, which aligns with GDPR's data minimization principle. Azure AI Vision logs can contain image metadata and analysis results that may include personal data, so disabling logging reduces GDPR compliance risk. Option E is correct because GDPR requires that personal data of EU residents be stored within the EU, and configuring a specific data residency region ensures compliance with this requirement.

Answer

Enable geo-redundant storage for the Azure AI Vision resource.

Answer

Enable Customer-Managed Keys (CMK) for encryption.

Answer

Use private endpoints to access the service.