Implement an agentic solution →hardMultiple ChoiceObjective-mapped

AI-102 Implement an agentic solution Practice Question

Exhibit

Refer to the exhibit.

{
  "assistant_id": "asst_abc123",
  "model": "gpt-4o",
  "tools": [
    {
      "type": "code_interpreter",
      "enabled": true
    },
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. San Francisco, CA"
            }
          },
          "required": ["location"]
        }
      }
    }
  ]
}

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?

⚠ Common exam trap

Candidates may assume that any GPT-4 model is supported, but Azure AI Agent Service has specific model availability. Always verify the model compatibility list for the service.

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 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 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 definition is missing the 'strict' parameter
Why it's wrong here
Incorrect. The 'strict' parameter is not a required field in function definitions for Azure AI Agent Service. The function definition only requires 'name', 'description', and 'parameters'.
✗
The 'code_interpreter' tool type should be 'code_interpreter' not 'code_interpreter'
Why it's wrong here
Incorrect. This option is nonsensical as it states the tool type should be 'code_interpreter' not 'code_interpreter', which is a contradiction. The correct tool type is 'code_interpreter', so this is not the issue.
✓
The model 'gpt-4o' is not supported
Why this is correct
Correct. The model 'gpt-4o' is not supported in Azure AI Agent Service, leading to configuration failure.
✗
The 'assistant_id' should be a thread ID
Why it's wrong here
Incorrect. The 'assistant_id' is correctly used to identify the assistant; it is not a thread ID, so this is not the issue.

Go deeper

AI-102 Implement an agentic solution Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question