AI-102 Practice Question: Implement natural language processing solutions
You are designing a solution to analyze customer call transcripts using Azure AI Language. The solution must extract key phrases, detect sentiment per utterance, and identify the customer's intent (e.g., 'cancel subscription', 'technical support'). The data is stored in Azure Blob Storage and processed in near real-time. Which combination of Azure AI Language features and processing pattern should you use?
⚠ Common exam trap
Candidates often assume prebuilt models (like CLU or sentiment analysis) are sufficient for custom intents and utterance-level analysis, overlooking the need for orchestration and custom training to handle domain-specific requirements.
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
✓
Use the conversation summarization API (with utterance-level sentiment and key phrase extraction) and an orchestration workflow model that routes to a custom conversational language understanding project for intent detection.
It combines the conversation summarization API (which provides utterance-level sentiment and key phrase extraction) with an orchestration workflow model that routes to a custom conversational language understanding (CLU) project for intent detection. This pattern supports near real-time processing of call transcripts from Azure Blob Storage, meeting the requirements for per-utterance sentiment, key phrase extraction, and intent identification.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use custom text classification to classify each utterance into intent categories and use the sentiment analysis API on the entire transcript.
Why it's wrong here
Custom text classification works on whole documents, not per utterance; also sentiment on the entire transcript loses per-utterance granularity.
- ✗
Use the prebuilt key phrase extraction API to identify important terms and the prebuilt sentiment analysis API for overall transcript sentiment, then map intents via a rules-based approach.
Why it's wrong here
Key phrase extraction does not detect intents; a rules-based approach is brittle and not scalable for multiple intents.
- ✓
Use the conversation summarization API (with utterance-level sentiment and key phrase extraction) and an orchestration workflow model that routes to a custom conversational language understanding project for intent detection.
Why this is correct
Conversation summarization provides utterance-level sentiment and key phrases; orchestration workflow allows routing to a custom CLU project for intent detection, handling multi-turn conversations effectively.
- ✗
Use the prebuilt conversational language understanding model for intent detection and Azure AI Language sentiment analysis API for utterance-level sentiment, processing each utterance independently via Azure Functions.
Why it's wrong here
The prebuilt CLU model is designed for common intents but does not provide sentiment per utterance; you would need a custom model for sentiment.
Quick reference
Azure Blob Storage Tier Comparison
| Tier | Storage Cost | Retrieval Cost | Latency | Use Case |
|---|---|---|---|---|
| Hot | Highest | Lowest | Immediate | Active data, frequent reads |
| Cool | Lower | Higher | Immediate | Data accessed < once / month |
| Cold | Lower still | Higher | Immediate | Data accessed < once / quarter |
| Archive | Lowest | Highest + rehydration delay | Hours | Long-term compliance retention |
Go deeper
Related to this question
About these practice questions
One of 945 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.