Implement an agentic solution →mediumMultiple ChoiceObjective-mapped

AI-102 Implement an agentic solution Practice Question

Exhibit

Refer to the exhibit.
{
  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
  "contentVersion": "1.0.0.0",
  "resources": [
    {
      "type": "Microsoft.Agents/agent",
      "apiVersion": "2024-12-01-preview",
      "name": "my-agent",
      "location": "eastus",
      "properties": {
        "displayName": "Customer Support Agent",
        "description": "Agent for customer support",
        "instructions": "You are a helpful assistant...",
        "model": {
          "format": "openai",
          "name": "gpt-4o-mini",
          "version": "2024-07-18"
        },
        "tools": [
          {
            "type": "code_interpreter",
            "enabled": true
          },
          {
            "type": "file_search",
            "enabled": false
          },
          {
            "type": "function",
            "function": {
              "name": "get_order_status",
              "description": "Get order status by order ID",
              "parameters": {
                "type": "object",
                "properties": {
                  "order_id": {
                    "type": "string"
                  }
                },
                "required": ["order_id"]
              }
            }
          }
        ],
        "conversation_starters": [
          {
            "text": "Check my order status"
          }
        ]
      }
    }
  ]
}

You deploy an agent using the ARM template shown. Users report that the agent cannot answer questions about uploaded documents. What is the most likely cause?

⚠ Common exam trap

Test-takers frequently assume file uploads automatically enable document Q&A, but Azure AI Agent Service requires explicit tool configuration—specifically enabling `file_search`—to index and query file content.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

The file_search tool is disabled in the agent configuration

The ARM template shown in the question likely configures the agent with the `file_search` tool set to `disabled` or omitted, which prevents the agent from indexing and querying uploaded documents. Without this tool enabled, the agent cannot perform retrieval-augmented generation (RAG) on file content, even if files are uploaded. Option C directly identifies this missing capability as the root cause.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
The function tool is missing required parameters
Why it's wrong here
Function parameters are correctly defined.
✗
The model specified is not supported for file operations
Why it's wrong here
Model supports file operations.
✓
The file_search tool is disabled in the agent configuration
Why this is correct
Disabled file_search prevents document search.
✗
The code_interpreter tool is enabled, which conflicts with file_search
Why it's wrong here
Code_interpreter does not conflict.

Go deeper

AI-102 Implement an agentic solution Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question