Plan and manage an Azure AI solution →hardMultiple Choice

AI-102 Plan and manage an Azure AI solution Practice Question

Exhibit

Refer to the exhibit.

```json
{
  "id": "1",
  "kind": "Conversation",
  "analysisInput": {
    "conversationItem": {
      "id": "1",
      "participantId": "user",
      "text": "I want to return my order #12345"
    }
  },
  "parameters": {
    "projectName": "SupportBot",
    "deploymentName": "production",
    "stringIndexType": "TextElement_V8"
  }
}
```

You are using Azure AI Language's conversational language understanding (CLU). The above JSON is a request to a CLU endpoint. What is the purpose of this request?

⚠ Common exam trap

Test-takers frequently confuse the CLU prediction endpoint with the training or deployment endpoints, mistakenly thinking a request with a 'query' field is used for model management rather than runtime inference.

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

✓

To predict the intent and entities from the user utterance

The JSON request is sent to the Azure AI Language CLU endpoint with a 'query' field containing the user utterance. The 'kind' field is set to 'Conversation', which triggers the CLU runtime to analyze the utterance against the deployed model. The purpose is to return a prediction of the top intent and any extracted entities, which is the core function of a conversational language understanding endpoint.

Answer analysis

Option-by-option breakdown

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

✓
To predict the intent and entities from the user utterance
Why this is correct
The request body supplies a user utterance to the CLU prediction endpoint, which returns the top-scoring intent plus any extracted entities. This satisfies the scenario's need to interpret a conversational input, since CLU's runtime API performs intent classification and entity extraction in a single call.
✗
To query a knowledge base for answers
Why it's wrong here
Knowledge-base querying belongs to Azure AI Search or question answering, not CLU, which extracts intents and entities from utterances rather than retrieving stored answers. It is tempting because both are Azure AI Language features, and would be correct when the source data is a document index.
✗
To deploy the CLU model to production
Why it's wrong here
Deployment is an authoring-plane action that assigns a trained model to a deployment name; the runtime endpoint only performs inference against an already-deployed model. Deployment is tempting because it also uses JSON, and would be correct when publishing a model version for production traffic.
✗
To train a new CLU model
Why it's wrong here
The request targets a runtime prediction endpoint, which returns extracted intents and entities; training is a separate authoring operation against the project's build endpoint. Training is tempting because it also consumes utterance JSON, and would be the correct purpose when submitting labelled examples to create or update a model.

Go deeper

AI-102 Plan and manage an Azure AI solution Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question