AI-102 Practice Test 43 — 15 Questions

Question 1

You are building a chat bot that uses Azure AI Language to process customer support tickets. The bot must extract entities like order numbers (e.g., ORD-12345) and issue categories. You need to choose the best approach for entity extraction to minimize development effort and ensure high accuracy.

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

Accepted Answer

Create a custom named entity recognition (NER) project in Azure AI Language that includes prebuilt components for order numbers and trains custom models for categories.. Azure AI Language's custom named entity recognition (NER) allows you to combine prebuilt components (like regex-based order number patterns) with custom-trained models for issue categories, minimizing development effort while achieving high accuracy. This approach leverages the built-in entity extraction capabilities of Azure AI Language without requiring intent classification or complex pipeline orchestration.

Answer

Leverage the Text Analytics for Health API to extract entities from the support tickets.

Answer

Use the Prebuilt Entity Extraction skill in Azure AI Search to extract order numbers and categories from the text.

Answer

Use the Conversational Language Understanding (CLU) project type to train a model for both intent and entity extraction.

Question 2

A company is deploying a generative AI solution using Azure OpenAI Service to generate product descriptions. The solution must comply with responsible AI principles, specifically ensuring that generated content does not include harmful or offensive language. Which Azure AI service feature should they implement to automatically filter the output?

Accepted Answer

Enable the default content filtering system in Azure OpenAI Service.. Azure OpenAI Service includes a built-in default content filtering system that automatically screens generated outputs for harmful or offensive language, aligning with responsible AI principles. This system operates at the service level without additional configuration, making it the simplest and most direct way to filter product descriptions for compliance.

Answer

Configure Prompt Shields in Azure AI Content Safety.

Answer

Use Azure AI Content Safety with a custom category severity threshold.

Answer

Use groundedness detection in Azure AI Content Safety.

Question 3

You are troubleshooting an Azure AI Search indexer that is failing with the error 'No skillset was found with the name 'skillset-name'.' The skillset exists in the same resource group. What is the most likely cause?

Accepted Answer

The indexer and skillset are in different Azure AI Search services.. The error 'No skillset was found with the name 'skillset-name'' indicates that the indexer cannot locate the skillset. The most likely cause is that the indexer and skillset are in different Azure AI Search services because skillsets are scoped to a specific search service and cannot be referenced across services. Option A (the indexer and skillset are in different Azure AI Search services) is correct. Option B is incorrect because while skillset names are case-sensitive, the error would likely be different if it were simply a typo or case mismatch. Option C is incorrect because the error is about the skillset, not the data source. Option D is incorrect because permission issues typically result in an authorization error, not a 'not found' error.

Answer

The skillset name has a typo or is case-sensitive.

Answer

The indexer's data source is misconfigured.

Answer

The indexer does not have permission to access the skillset.

Question 4

Which THREE are required to build a custom video indexing solution using Azure Video Analyzer for Media? (Choose three.)

Accepted Answer

An Azure Video Analyzer for Media account.. An Azure Video Analyzer for Media account is required because it is the core service that provides the video indexing capabilities, including AI-powered insights like speech transcription, face detection, and sentiment analysis. Without this account, you cannot access the indexing APIs or manage indexed videos.

Answer

A custom indexing pipeline.

Answer

A custom language model.

Question 5

A company uses Azure Form Recognizer to extract data from invoices. The extracted data contains many errors for a specific vendor's invoices. What should they do?

Accepted Answer

Custom train a model with labeled examples of that vendor's invoices.. Azure Form Recognizer's prebuilt invoice model may not generalize well to vendor-specific layouts or data formats. By custom training a model with labeled examples of that vendor's invoices, you adapt the extraction to the unique fields, tables, and formatting, significantly reducing errors. This leverages the service's supervised learning capability to improve accuracy for domain-specific documents.

Answer

Use a different prebuilt model.

Answer

Disable the OCR step.

Answer

Increase the confidence threshold.

Question 6

A company is using Azure OpenAI to generate customer support responses. They want to ensure the model does not use any personally identifiable information (PII) in its outputs. What should they implement?

Accepted Answer

Use Azure AI Content Safety to filter PII from the output.. Azure AI Content Safety provides built-in PII detection and redaction capabilities that can automatically scan and filter sensitive information from model outputs. This is the most reliable approach because it operates as a post-processing filter, catching PII that the model might generate despite instructions. Fine-tuning, prompt engineering, and system messages are all fallible because they rely on the model's compliance rather than enforced filtering.

Answer

Fine-tune the model on anonymized data.

Answer

Use prompt engineering to instruct the model to redact PII.

Answer

Use a system message instructing the model to avoid PII.

Question 7

You are developing an agentic solution that requires the agent to maintain context across multiple turns in a conversation. Which feature should you use to store and retrieve conversation history?

Accepted Answer

Threads. In the context of agentic solutions on Azure, threads are the correct feature for storing and retrieving conversation history across multiple turns. Threads maintain a sequential record of messages and tool calls, allowing the agent to reference prior context and maintain coherent multi-turn interactions. Sessions, vector stores, and memory serve different purposes and do not natively preserve conversational context in the same structured way.

Answer

Sessions

Answer

Vector store

Answer

Memory

Question 8

You review the configuration for an Azure AI Search indexer. The indexer runs successfully but no documents are indexed. What is the most likely cause?

Accepted Answer

The indexer does not have a skillset or field mappings to populate the 'content' field from the blob. When an Azure AI Search indexer runs successfully but indexes zero documents, the most common cause is that the indexer lacks a skillset or field mappings to extract and map the blob content (e.g., the 'content' field) into the search index. Without explicit field mappings or a skillset that defines how to populate the index fields from the blob's default properties, the indexer may complete execution without transferring any data into the index fields.

Answer

The connection string in the data source is invalid

Answer

The container name is incorrect

Answer

The maxFailedItems parameter is set to -1, which causes the indexer to skip all documents

Question 9

You are building an agentic solution using Azure AI Agent Service. The agent needs to retrieve information from a SQL database dynamically based on user input. Which tool should you configure within the agent to execute SQL queries?

Accepted Answer

Code Interpreter. (Code Interpreter) is correct because Azure AI Agent Service's Code Interpreter tool can execute Python code that uses libraries like `pyodbc` or `pymssql` to connect to a SQL database, run dynamic SQL queries based on user input, and return results. This allows the agent to retrieve information from a SQL database dynamically without requiring pre-defined function schemas or external API calls.

Answer

Function calling

Answer

Grounding with Bing

Answer

Kusto Query Language (KQL)

Question 10

A company uses Azure AI Language to analyze customer call transcripts. They need to identify specific entities such as product names and issue types. The prebuilt entity recognition does not cover their custom entities. Which approach should they take to extract both standard and custom entities from the transcripts?

Accepted Answer

Use a custom named entity recognition (NER) model for custom entities and call the prebuilt entity recognition API separately for standard entities.. Azure AI Language provides separate APIs for prebuilt entity recognition (covering standard entities like dates, numbers, and common types) and custom named entity recognition (NER) for domain-specific entities like product names and issue types. By using both services independently, you can extract standard entities from the prebuilt API and custom entities from a trained custom NER model, then combine the results. This approach avoids the limitations of a single model that cannot handle both predefined and custom entity types simultaneously.

Answer

Use the prebuilt entity recognition API only and map standard entities to custom categories.

Answer

Use a single conversational language understanding (CLU) project with entities defined for both standard and custom entities.

Answer

Use a custom text classification model to classify the transcript and then extract entities from the classified output.

Question 11

You are developing an agentic solution that uses Azure AI Agent Service with a custom function calling tool. The agent needs to call a function that requires authentication to an external API. How should you securely pass the API key to the function?

Accepted Answer

Use Azure Key Vault to store the API key and reference it in the function. Azure Key Vault provides a secure, centralized service for storing and managing secrets like API keys. In Azure AI Agent Service, you can configure the function to retrieve the API key at runtime from Key Vault using managed identities, ensuring the key is never exposed in code, configuration, or prompts. This follows the principle of least privilege and aligns with Azure's security best practices for agentic solutions.

Answer

Hardcode the API key in the function code

Answer

Store the API key in an environment variable

Answer

Pass the API key as part of the agent's system prompt

Question 12

Refer to the exhibit. You are configuring an Azure AI Search skillset. The skillset includes an EntityRecognitionSkill and a KeyPhraseExtractionSkill. After running the indexer, you notice that the 'organizations' field is empty in the index. What is the most likely cause?

Accepted Answer

The output field mapping for organizations is missing. The EntityRecognitionSkill outputs entities into a structured format (e.g., '/document/entities'). To populate the 'organizations' field in the index, you need to add a field mapping in the indexer that maps the skill output path (e.g., '/document/entities/organizations') to the index field. Without this mapping, the 'organizations' field remains empty. Option A is incorrect because the skill output path is typically correct; the issue is the missing field mapping. Option C is incorrect because the 'Organization' category is correctly spelled in the skill configuration. Option D is incorrect because the order of skills does not affect the output; entity recognition and key phrase extraction are independent.

Answer

The skill output path is incorrect

Answer

The 'Organization' category is misspelled

Answer

The skills must be in reverse order

Question 13

Which TWO actions should you take to improve the performance of a custom named entity recognition (NER) model in Azure AI Language?

Accepted Answer

Use a balanced dataset with similar numbers of examples for each entity.. A balanced dataset ensures the model learns to recognize all entity types equally, preventing bias toward overrepresented entities. In Azure AI Language custom NER, the model's performance depends on the quality and distribution of labeled data; an imbalanced dataset can lead to poor recall for minority entities.

Answer

Increase the training time of the model.

Answer

Reduce the number of entity types to simplify the model.

Answer

Use only prebuilt entity types to avoid training from scratch.

Question 14

Which THREE factors should be considered when choosing a region for deploying Azure AI services?

Accepted Answer

Service availability and feature support.. Service availability and feature support (Option B) is a critical factor because not all Azure AI services are available in every region; for example, certain Cognitive Services like Azure OpenAI or Computer Vision OCR may be in preview or fully supported only in specific regions. Choosing a region without the required service or feature would prevent deployment or limit functionality, directly impacting solution design.

Answer

Number of Azure data centers in the region.

Answer

Cost of the services in each region.

Question 15

You run the Azure CLI command shown in the exhibit to create an online endpoint for a generative AI model. The deployment fails because the selected VM instance type is not available in the East US region. Which action should you take to resolve the issue?

Accepted Answer

Specify a different VM type or region that supports Standard_NC6s_v3. The deployment failed because the Standard_NC6s_v3 VM instance type is not available in the East US region. The correct action is to either choose a different VM type that is available in East US or deploy to a different region that supports Standard_NC6s_v3. This directly addresses the root cause of the failure, as Azure Machine Learning online endpoints require the selected VM SKU to be available in the target region.

Answer

Increase the instance count to 2

Answer

Use a batch endpoint instead of online endpoint

Answer

Change --compute-type to CPU