AI-102 Plan and manage an Azure AI solution Practice Test 5 — 15 Questions

Question 1

Which TWO Azure services can be used to monitor and analyze the usage costs of an Azure AI solution that includes multiple Cognitive Services accounts?

Accepted Answer

Azure Cost Management + Billing. Azure Cost Management + Billing (C) provides native tools to track, analyze, and optimize cloud spending across all Azure services, including multiple Cognitive Services accounts. It allows you to break down costs by resource, resource group, or tag, and set budgets with alerts. Azure Monitor metrics and logs (E) can capture custom metrics and diagnostic logs from Cognitive Services, enabling you to correlate usage patterns with cost data for deeper analysis.

Answer

Azure Service Health

Answer

Azure Policy

Answer

Azure Advisor

Question 2

You need to provide a team of data scientists with access to an Azure Machine Learning workspace. The data scientists should be able to create and run experiments, but they should not be able to delete the workspace or modify its configuration. Which built-in role should you assign?

Accepted Answer

Contributor. The Contributor role allows creating and managing resources within the workspace, including experiments, but not deleting the workspace or modifying its configuration. Option B is wrong because Reader is read-only and cannot create experiments. Option C is wrong because User Access Administrator primarily manages user access and permissions, not resource creation. Option D is wrong because Owner grants full control, including the ability to delete the workspace and modify its configuration.

Answer

Reader

Answer

User Access Administrator

Answer

Owner

Question 3

You are deploying an Azure AI multi-agent solution on Microsoft Foundry. The solution uses three agents that must share context and pass tasks among themselves. To ensure reliable orchestration and traceability, which agent pattern should you implement?

Accepted Answer

Sequential agent pattern. The sequential agent pattern is correct because the scenario requires agents to share context and pass tasks among themselves in a reliable, traceable manner. In Microsoft Foundry, the sequential pattern ensures each agent executes in a defined order, passing state and results to the next agent, which provides clear orchestration and full traceability of the workflow.

Answer

Parallel agent pattern

Answer

Sub-agent pattern

Answer

Custom agent pattern

Question 4

Your team uses Azure AI Studio to deploy a large language model endpoint. You need to monitor for prompt injection attacks. Which Azure AI safety feature should you enable?

Accepted Answer

Azure AI Content Safety. Azure AI Content Safety is the correct feature because it provides built-in detection for prompt injection attacks by analyzing user inputs for malicious content, such as jailbreak attempts or indirect injection patterns. This service integrates directly with Azure AI Studio endpoints to filter harmful prompts before they reach the LLM, ensuring compliance with responsible AI practices.

Answer

Azure AI Agent Service

Answer

Azure AI Search

Answer

Azure OpenAI Service

Question 5

You need to restrict access to an Azure AI Language resource so that only a specific virtual network can call the endpoint. Which configuration should you use?

Accepted Answer

Enable a service endpoint or private endpoint for the resource. Azure AI Language resources can be isolated to a specific virtual network by enabling either a service endpoint (via the Microsoft.CognitiveServices service tag) or a private endpoint (using Azure Private Link). This configuration ensures that only traffic originating from the designated VNet can reach the resource's endpoint, effectively blocking all public internet access. Service endpoints provide a direct, optimized route from the VNet to the resource, while private endpoints assign a private IP from the VNet to the resource, making it accessible only within the VNet.

Answer

Rotate the shared access keys

Answer

Assign a managed identity to the resource

Answer

Configure an IP firewall rule with the VNet's public IP range

Question 6

You are designing a document processing pipeline using Azure AI Document Intelligence. The pipeline must extract data from both structured forms and unstructured invoices. The solution should support custom models with minimal manual labeling. Which approach should you use?

Accepted Answer

Train a custom neural model with a few labeled samples. Azure AI Document Intelligence's custom neural models can be trained with as few as five labeled samples, leveraging transfer learning to achieve high accuracy on both structured forms and unstructured invoices. This approach minimizes manual labeling effort while supporting the diverse document types in the pipeline, unlike prebuilt models that are limited to specific layouts or rule-based methods that require extensive manual configuration.

Answer

Use prebuilt invoice models for all documents

Answer

Use Azure AI Language to analyze text

Answer

Use OCR and custom regex patterns

Question 7

A healthcare organization uses Azure AI Health Insights to analyze patient data. They must ensure that PHI is not logged by the AI services. Which configuration should you apply?

Accepted Answer

Enable diagnostic settings to stream logs to a Log Analytics workspace with a data masking rule. Azure AI Health Insights processes protected health information (PHI), and enabling diagnostic settings to stream logs to a Log Analytics workspace with a data masking rule allows you to redact sensitive PHI from logs before they are stored. Data masking rules in Log Analytics can be configured to hide patterns like patient IDs or names, ensuring compliance with HIPAA while still retaining operational logs.

Answer

Disable all logging for the Azure AI resource

Answer

Configure the resource to use a system-assigned managed identity

Answer

Use Azure Policy to restrict logging to metadata only

Question 8

You are deploying a real-time translation service using Azure AI Translator. The solution must support automatic language detection and translation for customer chat conversations. Which pricing tier should you select to minimize costs while meeting the requirement?

Accepted Answer

Standard S1. The Standard S1 tier (D) is correct because it provides up to 1 million characters per month for translation and language detection, which is sufficient for typical customer chat workloads. The Free tier (F0) is limited to 2,000 characters per request and 2 million characters per month, which may be insufficient for production chat volumes. Higher tiers (S2, S3) offer increased throughput and character limits but incur higher costs, making S1 the most cost-effective choice that meets the requirement.

Answer

Free (F0)

Answer

Standard S3

Answer

Standard S2

Question 9

Your organization is using Azure AI Search with semantic ranking. Users report that search results are not showing relevant documents at the top. You need to improve relevance. What should you configure?

Accepted Answer

Enable semantic search configuration on the index. Semantic search configuration is required to enable semantic ranking, which uses deep learning models to re-rank search results based on contextual relevance rather than just keyword matching. Without this configuration, the index cannot leverage semantic ranking even if the service tier supports it, so enabling it directly addresses the user's complaint about irrelevant documents appearing at the top.

Answer

Add synonyms to the index

Answer

Define a custom scoring profile

Answer

Change the index analyzer to a different language analyzer

Question 10

You are responsible for an Azure AI multi-agent system built on Microsoft Foundry. The system experiences frequent timeout errors when agents call external APIs. You need to implement a resilient pattern. What should you do?

Accepted Answer

Implement retry logic with exponential backoff in the agent tool definitions. Implementing retry logic with exponential backoff in agent tool definitions is a standard resilience pattern for transient failures when calling external APIs. This approach, often using the Retry-After header or a custom backoff strategy, reduces load on the API and prevents cascading timeouts in a multi-agent system built on Microsoft Foundry. It aligns with the recommended practices for building robust AI solutions that depend on external services.

Answer

Disable retry attempts to avoid duplicate requests

Answer

Increase the global timeout for all agents

Answer

Switch to synchronous agent calls

Question 11

You deploy a custom vision model using Azure AI Custom Vision. After deployment, you notice the model has high accuracy on training data but low accuracy on new images. What is the most likely cause?

Accepted Answer

The model is overfitted to the training data. High accuracy on training data but low accuracy on new images is the classic symptom of overfitting, where the model has memorized the training examples (including noise and irrelevant patterns) rather than learning generalizable features. In Azure AI Custom Vision, this typically occurs when the training dataset is too small, too homogeneous, or lacks sufficient variation, causing the model to fail on unseen data.

Answer

The training time was too short

Answer

The training dataset has too few images

Answer

The wrong domain was selected during training

Question 12

Which TWO actions are required to enable private endpoint connectivity for an Azure AI Language resource?

Accepted Answer

Disable public network access on the AI resource. To enable private endpoint connectivity for an Azure AI Language resource, you must disable public network access on the AI resource (Option A) to ensure all traffic goes through the private endpoint. You also need to create the private endpoint in a subnet of a virtual network (Option B) to establish the private connection. Option C is not required because Azure Firewall rules are not needed for private endpoints; network policies are handled by NSG and UDR. Option D is incorrect because a private DNS zone is optional but not required—it is recommended for name resolution but not a requirement. Option E is wrong because service tags are not required for private endpoints; they are used for public network access rules.

Answer

Configure an Azure Firewall rule to allow the private endpoint

Answer

Create a private DNS zone for the resource

Answer

Add a service tag to the network security group

Question 13

Which THREE components are part of the Azure AI Foundry SDK for building multi-agent solutions?

Accepted Answer

AIAgentClient. Options A, B, and C are all correct. AIAgentClient is the core client for creating and managing agents, providing agent lifecycle and communication primitives for multi-agent solutions. AIProjectClient is used to manage the project context, including agent configurations and resources, and is essential for orchestrating agents within a project. InferenceClient handles inference calls to the underlying models, enabling agents to generate responses and perform tasks. Together, these three clients form the foundation of the Azure AI Foundry SDK for building multi-agent solutions.

Answer

Azure AI Search client

Answer

Azure OpenAI client

Question 14

Which TWO Azure AI services can be used to build a conversational AI system that handles multi-turn dialogues with context?

Accepted Answer

Azure AI Language. Azure AI Language provides conversational language understanding (CLU) capabilities that enable you to build a model capable of understanding multi-turn dialogues by maintaining context across user utterances. Azure OpenAI Service offers advanced language models like GPT-4, which can handle multi-turn conversations with context through prompt engineering and conversation history, making it suitable for building conversational AI systems.

Answer

Azure AI Search

Answer

Azure AI Content Safety

Answer

Azure AI Bot Service

Question 15

Refer to the exhibit. You are deploying an AI project in Microsoft Foundry using an ARM template. The deployment fails with an error indicating that the hub resource is not in the same region. What is the most likely cause?

Accepted Answer

The hub and project are in different Azure regions. In Azure AI Foundry, the hub and project resources must reside in the same Azure region because the project is a child resource of the hub and relies on the hub's regional endpoint for metadata storage and compute orchestration. The ARM template deployment fails with a region mismatch error when the location property of the project specifies a different region than the hub's location, as Azure enforces regional affinity for child resources to ensure low-latency communication and data residency compliance.

Answer

The resource group for the hub is different from the project's resource group

Answer

The identity type is SystemAssigned, but the hub requires UserAssigned

Answer

The location property is misspelled in the template