AI-102 Implement an agentic solution Practice Test 3 — 15 Questions

Question 1

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. The Code Interpreter tool allows the agent to execute code, including SQL queries, against data sources. Function calling is for invoking custom APIs, not direct SQL execution. Grounding with Bing is for web search. KQL is for Azure Data Explorer.

Answer

Function calling

Answer

Grounding with Bing

Answer

Kusto Query Language (KQL)

Question 2

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 Microsoft Foundry to enable agent-to-agent communication?

Accepted Answer

Use Agent Handoff feature. Agent Handoff is a built-in feature in Microsoft Foundry that allows one agent to pass control to another agent along with context. Custom API integration is possible but not the designed approach. Shared memory is for state management, not handoff. Sequential orchestration is manual.

Answer

Configure a shared memory store

Answer

Implement a custom API for agent communication

Answer

Orchestrate agents sequentially using a script

Question 3

You are deploying an agentic solution using Azure AI Agent Service. The agent needs to be invoked from a custom application using REST API calls. Which endpoint should you use to send a message to the agent?

Accepted Answer

POST /threads/{thread_id}/messages. The correct endpoint is /threads/{thread_id}/messages to send a message. /threads creates a thread, /runs executes the agent, and /agents is for management.

Answer

POST /threads/{thread_id}/runs

Answer

POST /threads

Answer

GET /agents

Question 4

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. Threads in Azure AI Agent Service are designed to store conversation history and maintain context. Memory is a generic term, not specific to the service. Vector stores are for embeddings. Sessions are for containerized apps.

Answer

Sessions

Answer

Vector store

Answer

Memory

Question 5

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. OAuth 2.0 authorization code flow with PKCE is the recommended approach for delegated permissions in native apps that need to act on behalf of a user. Client credentials flow is for app-only access. Implicit flow is deprecated. Device code flow is for devices without a browser.

Answer

OAuth 2.0 client credentials flow

Answer

OAuth 2.0 implicit flow

Answer

OAuth 2.0 device code flow

Question 6

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. Knowledge base tool (or file search / grounding) is used to connect to Azure AI Search index. Code Interpreter is for code execution. Function calling is for APIs. KQL is for Azure Data Explorer.

Answer

Code Interpreter

Answer

Function calling

Answer

KQL

Question 7

You are troubleshooting an agentic solution where the agent is not returning responses within acceptable time limits. You suspect the agent is making too many sequential calls to external tools. Which strategy should you recommend to reduce latency?

Accepted Answer

Enable parallel tool execution. Parallel tool execution reduces latency by running independent tool calls concurrently. Adding more tools increases load. Increasing token limit does not help with tool call latency. Reducing thread history might affect context but not tool call speed.

Answer

Increase the max token limit

Answer

Add more tools to distribute the load

Answer

Reduce the thread history length

Question 8

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. Using Azure Key Vault references in the function code is the secure way to retrieve secrets at runtime without exposing them. Hardcoding is insecure. Environment variables may be exposed. Passing in the prompt leaks credentials.

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 9

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 10

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. Code Interpreter can execute SQL queries via Python. Function calling can be used to invoke custom database operations. Knowledge base is for search, not write. KQL is for Azure Data Explorer.

Answer

KQL

Answer

Grounding with Bing

Answer

Knowledge base

Question 11

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. Data residency requires storing and processing data within the EU region. Using Azure regions in the EU, configuring data storage in those regions, and enabling data encryption at rest are key compliance measures. Global regions may violate residency. Disabling logging may hinder auditing.

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 12

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. Agent Handoff, Threads, and Shared Memory are key features for context preservation and handoff. Function calling is for tool integration, not handoff. KQL is for queries.

Answer

KQL

Answer

Function calling

Question 13

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 function definition is missing the 'strict' parameter. The function definition is missing the 'strict' parameter, which is required for function calling in the current API. The other parameters are correct. The model name is valid, and the code_interpreter tool is correctly enabled.

Answer

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

Answer

The model 'gpt-4o' is not supported

Answer

The 'assistant_id' should be a thread ID

Question 14

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 'strict' parameter in the function definition. The function definition is missing the 'strict' parameter, which is required for the model to understand the function schema correctly. The other fields are present. The tool_choice is set to auto, which is correct.

Answer

The 'messages' array should include a system prompt

Answer

The 'tool_choice' should be 'required'

Answer

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

Question 15

Refer to the exhibit. You have created an assistant with the above configuration. When you send a message 'What is the weather in Seattle?', the assistant responds without calling the function. What is the most likely cause?

Accepted Answer

The function is missing the 'description' property. The function definition is missing the 'description' field, which is required for the model to understand when to call the function. The instructions say to call the function, but the model relies on the function's description. The other settings are correct.

Answer

The 'instructions' are not being followed

Answer

The 'strict' parameter is set to true

Answer

The 'tool_resources' code_interpreter has empty file_ids