Implement natural language processing solutions →mediumMultiple Choice

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Refer to the exhibit.
```json
{
  "kind": "Conversation",
  "analysisInput": {
    "conversationItem": {
      "id": "1",
      "participantId": "user",
      "text": "Book a flight from Seattle to New York on June 15th."
    }
  },
  "parameters": {
    "projectName": "FlightBooking",
    "deploymentName": "production",
    "stringIndexType": "TextElement_V8"
  }
}
```

Refer to the exhibit. You submit this request to Azure AI Language's conversational language understanding (CLU) for the 'FlightBooking' project. The model correctly identifies the intent as 'BookFlight' and extracts entities: 'Seattle' as FromCity, 'New York' as ToCity, and 'June 15th' as Date. What is the next step for the application?

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

✓

Call a separate booking API with the extracted entities to complete the reservation.

After CLU extracts the intent and entities, the application must use those entities to call a separate booking API to complete the reservation. CLU itself does not perform bookings; it only provides language understanding. Option B is incorrect because the CLU response cannot directly book a flight. Option C is incorrect because the intent is already clearly identified as 'BookFlight' and entities are extracted, so no rephrasing is needed. Option D is incorrect because sending another request to CLU would not confirm booking; confirmation is handled by the booking API.

Answer analysis

Option-by-option breakdown

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

✓
Call a separate booking API with the extracted entities to complete the reservation.
Why this is correct
CLU returns only intent and entity predictions; it performs no booking action itself. The application must pass the extracted FromCity, ToCity and Date values to a separate booking API to complete the reservation, which is the required next step.
✗
Use the CLU response to directly book the flight via the Azure AI Language service.
Why it's wrong here
Azure AI Language's CLU only returns predicted intents and extracted entities; it performs no booking, so the application must call its own reservation backend. It is tempting because the response looks complete, and chaining CLU output into a fulfilment API would be correct once that downstream booking service exists.
✗
Prompt the user to rephrase the request because the intent is ambiguous.
Why it's wrong here
CLU returned a confident intent with all three required entities populated, so no ambiguity exists to justify asking the user to rephrase. It is tempting because rephrasing prompts are standard when confidence scores fall below threshold or entities are missing, which is not the case here.
✗
Send another request to CLU to confirm the booking details.
Why it's wrong here
CLU returns intent and entity predictions only; it holds no booking state, so a second call cannot confirm anything. The application must act on the extracted FromCity, ToCity and Date values itself, typically by calling a booking API. Re-querying is tempting because multi-turn CLU projects use follow-up utterances to gather missing slots, but here all required entities were already extracted.

Go deeper

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question