AI-102 Practice Exam 4 — 20 Questions

Question 1

You are building a generative AI solution using Azure AI Foundry. The solution must meet compliance requirements that require all model inputs and outputs to be auditable for a minimum of one year. What should you enable?

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

Accepted Answer

Diagnostic settings to capture request and response logs and store them in a storage account.. Enabling diagnostic settings for the Azure AI Foundry resource allows you to capture detailed request and response logs for all model interactions. By routing these logs to a storage account, you retain the data for the required one-year audit period, meeting compliance needs for full traceability of inputs and outputs.

Answer

Azure Monitor alerts for unusual activity.

Answer

Azure Monitor metrics for the Azure AI Foundry resource.

Answer

Azure Monitor workbooks to visualize usage.

Question 2

You are using Azure OpenAI Service to generate product descriptions. The output is often too verbose. You need to reduce the length of generated text without changing the model. Which parameter should you adjust?

Accepted Answer

Max tokens. Max tokens controls the total length of the generated response by capping the number of tokens (words/subwords) the model can output. Reducing this value directly truncates the output, making descriptions shorter without altering the model or its behavior. Other parameters influence randomness or repetition but do not enforce a strict length limit.

Answer

Frequency penalty

Answer

Temperature

Answer

Top-p (nucleus sampling)

Question 3

You are developing a generative AI application that uses Azure OpenAI Service to summarize large documents. The application experiences high latency when processing requests. You need to reduce the latency without changing the model. What should you do?

Accepted Answer

Reduce the max_tokens parameter in the API request. Reducing the max_tokens parameter limits the length of the generated response, which directly reduces the processing time required by the Azure OpenAI Service to produce the output. Since latency is caused by the model generating a long sequence of tokens, capping the output tokens decreases the number of autoregressive decoding steps, thereby lowering response time without altering the underlying model.

Answer

Increase the temperature parameter

Answer

Increase the top_p parameter

Answer

Increase the max_tokens parameter

Question 4

You are reviewing the ARM template snippet for an Azure AI Foundry hub. After deployment, you notice that the hub cannot connect to the storage account. What is the most likely cause?

Accepted Answer

The hub uses a managed network that blocks outbound traffic to the storage account. The most likely cause is that the hub uses a managed network which, by default, blocks outbound traffic to the storage account unless explicitly allowed via outbound rules or private endpoints. Azure AI Foundry hubs enforce network isolation for security, and if the storage account is not configured as an approved destination, the hub cannot establish the required connections for data access.

Answer

The location 'eastus' does not support AI Foundry hubs

Answer

The storage account name contains invalid characters

Answer

The key vault is not configured with a firewall rule

Question 5

A legal firm is using Azure AI Language to analyze contracts. They need to extract key clauses, parties involved, and dates. The solution must be customizable to their specific contract types. Which TWO Azure AI Language features should they use?

Accepted Answer

Prebuilt NER for Legal. Prebuilt NER for Legal is correct because it provides out-of-the-box entity extraction tailored to legal documents, including parties, dates, and key clauses, without requiring custom training. This feature is specifically designed for legal use cases, making it ideal for a firm that needs to quickly extract standard legal entities from contracts.

Answer

Conversation summarization

Answer

Key phrase extraction

Answer

Entity linking

Question 6

A company uses Azure OpenAI to generate code snippets. They notice that the model sometimes produces code that uses deprecated APIs. They want to minimize this without retraining the model. What should they do?

Accepted Answer

Add a system message instructing the model to use only current, non-deprecated APIs.. Adding a system message in Azure OpenAI allows you to set high-level instructions that guide the model's behavior without retraining. By explicitly instructing the model to use only current, non-deprecated APIs, you leverage the system prompt's ability to influence output style and content, effectively reducing deprecated API usage in generated code snippets.

Answer

Fine-tune the model on a dataset of recent code.

Answer

Set the temperature parameter to 0 to reduce randomness.

Answer

Provide a few-shot example of correct code in the prompt.

Question 7

Which TWO features of Azure AI Content Safety can help you moderate user-generated content in a social media application?

Accepted Answer

Self-harm content detection.. Self-harm content detection (A) is a feature of Azure AI Content Safety that specifically identifies text or images related to self-harm, which is a critical category for moderating user-generated content in social media to prevent harm and comply with safety policies. Hate speech severity detection (B) is another core feature that classifies hate speech into severity levels (e.g., low, medium, high), enabling nuanced moderation of offensive content.

Answer

PII redaction.

Answer

Groundedness detection.

Answer

Prompt injection detection.

Question 8

You are designing a computer vision solution for a retail chain to detect shelf stockouts using store camera feeds. Videos are processed in near real-time. Which combination of Azure services should you use to minimize latency and cost?

Accepted Answer

Use Azure Video Analyzer for Media (formerly Video Indexer) with an Azure IoT Edge module processing video at the edge.. Azure Video Analyzer for Media (formerly Video Indexer) with an Azure IoT Edge module enables near real-time processing at the edge, minimizing latency by avoiding round trips to the cloud, and reduces cost by processing video locally and only sending relevant insights (e.g., stockout detections) to the cloud. This architecture is ideal for retail chains with store camera feeds that require low-latency, cost-effective stockout detection.

Answer

Use Azure Video Indexer to analyze videos and send results to Azure SQL Database.

Answer

Use Azure Custom Vision to detect stockouts in video frames.

Answer

Use Azure Media Services to transcode video and then run Custom Vision on key frames.

Question 9

You are deploying a generative AI solution using Azure OpenAI Service. You need to monitor the usage and costs associated with the service. What should you use?

Accepted Answer

Azure Monitor. Azure Monitor is the correct choice because it provides detailed metrics, logs, and alerts for Azure OpenAI Service usage, including token consumption, request counts, and latency. This data is essential for tracking costs and usage patterns, as Azure OpenAI charges based on tokens processed. Azure Monitor integrates directly with the service to surface these operational metrics.

Answer

Microsoft Purview

Answer

Azure Advisor

Answer

Azure Cost Management

Question 10

Refer to the exhibit. You are configuring a system message for an Azure OpenAI deployment. The assistant is still generating harmful code despite the instruction. Which additional measure should you implement?

Accepted Answer

Enable Azure AI Content Safety with a custom blocklist for harmful code.. Azure AI Content Safety provides a dedicated content filtering layer that can block harmful code generation at the inference level, regardless of the system message. A custom blocklist allows you to define specific patterns (e.g., code snippets for malware) that the model is prohibited from outputting, enforcing safety beyond prompt instructions.

Answer

Fine-tune the model on safe code examples.

Answer

Lower the temperature parameter to 0.

Answer

Add more examples to the prompt.

Question 11

Your organization uses Microsoft Syntex to automatically classify and extract metadata from documents stored in SharePoint. You need to extend this capability to also extract entities such as invoice numbers and dates from PDF invoices that are uploaded to SharePoint. What should you do?

Accepted Answer

Create a document understanding model in Syntex that extracts entities from invoices.. Microsoft Syntex document understanding models can classify documents and extract entities such as invoice numbers and dates. Option A is incorrect because Syntex does not use AI Builder's out-of-the-box entity extraction; it uses its own model training. Option B is incorrect because Azure AI Search is a search service, not an entity extraction service integrated with Syntex. Option C is incorrect because Power Automate with AI Builder is a separate workflow automation approach, not part of Syntex. Therefore, option D is correct: create a document understanding model in Syntex that extracts entities from invoices.

Answer

Create a custom entity extraction model in Syntex using AI Builder.

Answer

Integrate Azure AI Search with SharePoint to extract entities.

Answer

Use Power Automate with AI Builder to extract entities from invoices.

Question 12

Refer to the exhibit. You are using Microsoft Graph to retrieve user information for use in a Microsoft 365 Copilot extension. The response shows that the mail and mobilePhone fields are null. What is the most likely reason?

Accepted Answer

The user has not configured those properties in their Microsoft Entra ID profile.. The mail and mobilePhone fields are null because the user has not populated these attributes in their Microsoft Entra ID (formerly Azure AD) profile. Microsoft Graph returns the actual stored values for these properties; if they are empty or unset, the API response will show null. This is the most common and straightforward reason for null values in user profile fields.

Answer

The API call required additional permissions.

Answer

The user is a guest user.

Answer

The user does not exist in the tenant.

Question 13

You need to provision an Azure AI Language resource that supports custom text classification. Which pricing tier should you select to use the custom training feature?

Accepted Answer

Standard (S). The Standard (S) tier is the only pricing tier for Azure AI Language that supports custom text classification, including the custom training feature. The Free (F0) tier is limited to pre-built capabilities and cannot be used for training custom models, while Basic (B) and Premium (P) tiers do not exist for this service.

Answer

Free (F0)

Answer

Basic (B)

Answer

Premium (P)

Question 14

You are using Azure AI Document Intelligence to extract data from scanned contracts. The contracts contain tables and handwritten signatures. Which TWO features should you enable?

Accepted Answer

Train a custom neural model to recognize handwritten signatures.. Options A and B are correct because a custom neural model can be trained to recognize handwritten signatures (A), and enabling table extraction in the custom model extracts tables from contracts (B). Option C is incorrect because OCR is already enabled by default in Document Intelligence and does not need to be separately enabled. Option D is wrong because form recognition for key-value pairs is not required for this scenario, as the focus is on tables and signatures. Option E is wrong because the prebuilt-layout model does not support custom training for signature recognition and may not handle handwritten elements as accurately as a custom model.

Answer

Enable OCR to read scanned text.

Answer

Use form recognition to capture key-value pairs.

Answer

Use the prebuilt-layout model for all extraction.

Question 15

Refer to the exhibit. You are deploying an agent in Microsoft Foundry using the ARM template snippet above. The agent needs to call Microsoft Graph API to reset a user's password. However, the deployment fails with an authorization error. What is the most likely cause?

Accepted Answer

The managed identity does not have the 'User.ReadWrite.All' delegated permission for Microsoft Graph.. The agent uses a managed identity to authenticate to Microsoft Graph, and the error indicates an authorization failure. For the agent to call Graph API to reset a user's password, the managed identity must be granted the 'User.ReadWrite.All' application permission (not delegated) via an API permission assignment in Azure AD. Without this permission, the Graph API returns a 403 Forbidden error, even if the endpoint and ARM template syntax are correct.

Answer

The Graph API endpoint URL is incorrect.

Answer

The apiVersion '2025-01-01-preview' is not supported for agent deployments.

Answer

The resourceId for managed identity is missing the 'Microsoft.ManagedIdentity/userAssignedIdentities' resource type.

Question 16

A company is using Azure Cognitive Service for Language to analyze customer support transcripts. They want to identify custom categories (e.g., 'billing', 'technical support') using a custom text classification model. After training and deploying the model, they receive many false positives for the 'billing' category. What is the best first step to improve model accuracy?

Accepted Answer

Review the training data for the 'billing' category and correct any mislabeled examples.. False positives for a specific category like 'billing' most often stem from mislabeled or ambiguous training examples in that category. By reviewing and correcting the training data for 'billing', you directly address the root cause of the model's confusion, which is the most effective first step in custom text classification model improvement.

Answer

Add more training data to all categories to improve overall model performance.

Answer

Use a different Azure AI service, such as key phrase extraction, to identify billing-related content.

Answer

Increase the confidence threshold for the 'billing' category to reduce false positives.

Question 17

You are responsible for an Azure AI solution that uses Custom Vision to classify manufacturing defects. The model must achieve high recall to avoid missing defects. The current model has high precision but low recall. Which action should you take?

Accepted Answer

Lower the probability threshold for the defect class. Lowering the probability threshold for the defect class means the model will classify an image as defective even when its confidence score is lower. This increases the number of true positives (defects caught), directly improving recall at the cost of potentially more false positives. In Custom Vision, the default probability threshold is 50%, and adjusting it downward is the standard technique to prioritize recall over precision.

Answer

Add more images of non-defective items to the training set

Answer

Increase the number of training iterations

Answer

Increase the probability threshold for the defect class

Question 18

A company is building a chatbot using Azure AI Language. The chatbot must understand user intents and extract entities like dates and locations. The solution should minimize manual labeling effort. Which feature should the team use?

Accepted Answer

CLU prebuilt entity components. CLU prebuilt entity components provide ready-made entity extraction for common types like dates and locations without requiring manual labeling. This minimizes manual effort while still allowing the chatbot to understand user intents and extract entities, as the prebuilt components are domain-agnostic and cover a wide range of entity types out of the box.

Answer

Conversational Language Understanding (CLU) Orchestration Workflow

Answer

CLU prebuilt intents

Answer

Azure AI QnA Maker

Question 19

Which TWO Azure AI services can be used to detect objects in images?

Accepted Answer

Custom Vision. Custom Vision (Option C) is correct because it allows you to train a custom image classification or object detection model using your own labeled images. You can upload images, tag objects with bounding boxes, and then use the trained model to detect specific objects in new images, making it a valid choice for object detection tasks.

Answer

Video Indexer

Answer

Face API

Answer

Azure AI Document Intelligence

Question 20

Which TWO Azure AI services can be used to build a conversational chatbot that uses generative AI? (Choose two.)

Accepted Answer

Azure AI Bot Service. Azure AI Bot Service (B) provides a dedicated platform for building, deploying, and managing conversational chatbots, integrating with channels like Microsoft Teams and Slack. Azure OpenAI Service (E) enables generative AI capabilities by providing access to large language models (e.g., GPT-4) that can generate human-like responses, making it ideal for powering the conversational intelligence of a chatbot.

Answer

Azure AI Search

Answer

Azure AI Translator

Answer

Azure AI Language