AI-102 Implement an agentic solution Practice Test 2 — 15 Questions

Question 1

You need to monitor an agent deployed in Microsoft Foundry. Which Azure service should you use to collect and analyze logs and metrics from the agent?

Accepted Answer

Azure Monitor. Azure Monitor is the correct choice because it is the comprehensive monitoring service for Azure resources, including agents deployed in Microsoft Foundry. It collects and analyzes logs and metrics from the agent, providing a unified view of performance and health. Application Insights is a subset of Azure Monitor focused on application performance monitoring (APM), but for general agent monitoring, Azure Monitor is the primary service.

Answer

Application Insights

Answer

Azure Log Analytics

Answer

Microsoft Sentinel

Question 2

Refer to the exhibit. You deploy this ARM template to create an agent. The agent uses a user-assigned managed identity to call an external weather API. The deployment succeeds but the agent fails to authenticate to the weather API. What is the most likely reason?

Accepted Answer

The external weather API is not configured to accept tokens from the managed identity's tenant.. The agent uses a user-assigned managed identity to authenticate to an external weather API. Managed identities provide tokens that are valid only within the Microsoft Entra ID (formerly Azure AD) tenant where the identity is registered. For the agent to successfully authenticate, the external weather API must be configured as an application in that same tenant and trust tokens issued by that tenant. Option D correctly identifies that the most likely reason for authentication failure is that the external weather API is not configured to accept tokens from the managed identity's tenant, meaning the API does not trust the token issuer.

Answer

The resourceId for the managed identity is incorrect.

Answer

The model provider 'AzureAI' should be 'AzureOpenAI'.

Answer

The URL parameter is missing the API version.

Question 3

You are creating an agent in Microsoft Copilot Studio that needs to escalate to a human agent when it cannot resolve a query. Which feature should you use?

Accepted Answer

Add a 'Transfer to agent' topic.. In Microsoft Copilot Studio, the 'Transfer to agent' topic is the correct feature to escalate unresolved queries to a human agent. This topic is specifically designed to hand off the conversation to a live agent, often by triggering a handoff mechanism such as a Dynamics 365 Customer Service queue or a custom integration. It ensures that the bot gracefully transfers context and conversation history, maintaining a seamless user experience.

Answer

Add an 'Escalate' system topic.

Answer

Configure the 'Fallback' topic to call a Power Automate flow.

Answer

Use the 'End conversation' node.

Question 4

You deploy an agent in Microsoft Foundry that uses a custom skill in Azure AI Search. The skill calls an Azure Function to enrich documents. The function uses an API key. The deployment succeeds but the skill returns an error when processing documents. The function logs show the request is received but the API key is missing. What is the most likely cause?

Accepted Answer

The skill definition does not include the apiKey in the header.. The custom skill definition in Azure AI Search must include an `apiKey` property in the header to authenticate requests to the Azure Function. Since the function logs show the request is received but the API key is missing, the most likely cause is that the skill definition omitted the `apiKey` header. This is a common configuration error when setting up custom skills with HTTP-triggered functions.

Answer

The Azure Function is not running.

Answer

The API key stored in Azure Key Vault is expired.

Answer

The custom skill's URI is incorrect.

Question 5

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 6

You are developing an agentic solution that uses multiple AI agents to collaborate on a complex task. To ensure the agents work together effectively, you need to define a clear handoff protocol. Which approach should you use in Azure AI Agent Service to enable agent-to-agent communication?

Accepted Answer

Use Agent Handoff feature. Azure AI Agent Service provides a built-in Agent Handoff feature that enables seamless agent-to-agent communication by defining a structured handoff protocol. This feature allows agents to pass tasks and context to each other without custom code, ensuring efficient collaboration in multi-agent systems.

Answer

Configure a shared memory store

Answer

Implement a custom API for agent communication

Answer

Orchestrate agents sequentially using a script

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 are building an agentic solution that needs to perform actions on behalf of the user, such as sending emails and updating calendars. Which authentication approach should you use for the agent to access Microsoft Graph API with delegated permissions?

Accepted Answer

OAuth 2.0 authorization code flow with PKCE. The authorization code flow with PKCE is the correct approach because the agent needs to act on behalf of a signed-in user, requiring delegated permissions. This flow securely exchanges an authorization code for an access token, and PKCE adds a cryptographic challenge to prevent interception attacks, making it ideal for public clients like agent applications.

Answer

OAuth 2.0 client credentials flow

Answer

OAuth 2.0 implicit flow

Answer

OAuth 2.0 device code flow

Question 9

You are designing an agentic solution that uses Azure AI Agent Service to answer customer support queries. The agent needs to retrieve information from a knowledge base stored in Azure AI Search. Which tool should you enable for the agent?

Accepted Answer

Knowledge base. The Knowledge base tool is the correct choice because it is specifically designed to connect an Azure AI Agent to an Azure AI Search index, enabling retrieval-augmented generation (RAG) from structured or unstructured knowledge sources. This tool allows the agent to query the search index and return relevant chunks of information to answer customer support queries without custom code.

Answer

Code Interpreter

Answer

Function calling

Answer

KQL

Question 10

You are building an agentic solution that needs to process large documents uploaded by users. The agent should extract key information and summarize the content. Which tool should you enable?

Accepted Answer

Code Interpreter. Code Interpreter (now called 'Code Interpreter' in Azure AI Studio/Assistants API) provides a sandboxed Python environment that can execute code to process uploaded files, including parsing large documents, extracting key information, and generating summaries. It handles file I/O, data manipulation, and natural language processing libraries, making it the correct tool for this agentic document-processing task.

Answer

Function calling

Answer

KQL

Answer

Knowledge base

Question 11

You are designing an agentic solution using Azure AI Agent Service. The agent needs to be able to both read and write data to an Azure SQL database. Which TWO tools should you configure?

Accepted Answer

Function calling. Function calling (A) is correct because it lets the agent invoke custom functions that execute parameterized T-SQL statements (for example, INSERT, UPDATE, DELETE, or SELECT) against the Azure SQL database, providing the read/write capability the scenario requires. Code Interpreter (D) is correct because it runs Python code in a sandboxed environment where the agent can use libraries such as pyodbc or sqlalchemy to connect to Azure SQL and perform both read and write operations programmatically. KQL (B) is not appropriate because it targets Azure Data Explorer / Log Analytics query endpoints, not Azure SQL, and is primarily read-oriented. Grounding with Bing (C) only supplies web search grounding and cannot write to a database. Knowledge base (E) is a retrieval/grounding construct for search over indexed content and does not provide write access to Azure SQL.

Answer

KQL

Answer

Grounding with Bing

Answer

Knowledge base

Question 12

You are deploying an agentic solution that must comply with data residency requirements. The agent processes personal data from users in the European Union. Which THREE actions should you take to ensure compliance?

Accepted Answer

Deploy the agent service in an Azure region within the European Union. Option A is correct because deploying the agent service in an Azure region within the European Union ensures that data processing and storage occur within EU boundaries, directly satisfying data residency requirements for EU personal data. Option C is correct because enabling encryption at rest with customer-managed keys (CMK) in Azure Key Vault gives the organization control over the encryption keys protecting personal data, which supports compliance with GDPR requirements for safeguarding personal data. Option E is correct because storing all agent data in an Azure SQL Database located in the EU region ensures that the data persists within EU boundaries, maintaining residency compliance for stored personal data. Option B is not correct because disabling logging does not address data residency and may violate audit and accountability requirements under GDPR. Option D is not correct because a globally redundant storage account replicates data to regions outside the EU, which would violate data residency requirements.

Answer

Disable logging for the agent to avoid storing personal data

Answer

Configure the agent's data storage to use a globally redundant storage account

Question 13

You are developing an agentic solution that uses multiple agents to handle customer inquiries. You need to ensure that agents can hand off to each other with full context. Which THREE features should you use?

Accepted Answer

Shared Memory. Shared Memory (B) is correct because it provides a common store where multiple agents can read and write conversational state, ensuring that context such as user details, prior turns, and intermediate results persists across agent boundaries. Agent Handoff (C) is correct because it is the explicit mechanism that transfers control from one agent to another while carrying the accumulated context, which is exactly what the scenario requires for seamless multi-agent collaboration. Threads (D) is correct because a thread maintains the ordered conversation history and message state that agents attach to, so a handoff can continue the same logical conversation rather than starting a new one. KQL (A) is a query language for logs and telemetry, not a context-sharing or handoff feature, and Function calling (E) lets an agent invoke tools or APIs but does not by itself preserve or transfer conversational context between agents.

Answer

KQL

Answer

Function calling

Question 14

Refer to the exhibit. You are configuring an agent in Azure AI Agent Service. You want the agent to be able to execute Python code and call a custom function to get weather data. What is the issue with the JSON configuration?

Accepted Answer

The model 'gpt-4o' is not supported. The Azure AI Agent Service currently does not support the gpt-4o model for assistants. The supported models include GPT-4, GPT-4-turbo, and GPT-4-32k. Using an unsupported model will cause the agent to fail during configuration or runtime.

Answer

The function definition is missing the 'strict' parameter

Answer

The 'code_interpreter' tool type should be 'code_interpreter' not 'code_interpreter'

Answer

The 'assistant_id' should be a thread ID

Question 15

Refer to the exhibit. You are sending a request to an agent using the Chat Completions API. The agent should decide whether to call the 'get_weather' function or not. What is missing from the request to enable the agent to properly use the function?

Accepted Answer

The 'messages' array should include a system prompt. A system prompt is missing. In the Chat Completions API, a system message sets the behavior and context for the assistant. Without it, the agent may not understand when to call the 'get_weather' function. The system prompt should instruct the assistant to use the function when appropriate.

Answer

The 'tool_choice' should be 'required'

Answer

The 'model' should be 'gpt-4o-mini'

Answer

The 'strict' parameter in the function definition