AI-102 Plan and manage an Azure AI solution Practice Question
You are designing a chatbot using Azure AI Language. The chatbot must understand user intents and also extract entities like dates and locations. Which feature combination should you use?
⚠ Common exam trap
Many exam-takers confuse entity linking (which maps to external knowledge bases) with entity extraction (which pulls values directly from the utterance), leading them to choose Option B despite it lacking intent recognition.
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
✓
Conversational Language Understanding (CLU) with entities
Conversational Language Understanding (CLU) is the correct Azure AI Language feature for building a chatbot that understands user intents and extracts entities like dates and locations. CLU is specifically designed for natural language understanding (NLU) tasks, providing prebuilt and custom entity extraction alongside intent recognition, which directly matches the requirement.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Conversational Language Understanding (CLU) with entities
Why this is correct
Conversational Language Understanding provides intent classification alongside integrated entity extraction, satisfying both requirements in one Azure AI Language resource. Custom entities capture dates and locations through labelled training utterances, unlike sentiment analysis or key phrase extraction, which return no intent predictions. CLU therefore meets the stem's dual constraint without combining separate services.
- ✗
Sentiment analysis and entity linking
Why it's wrong here
Sentiment analysis scores opinion polarity and entity linking resolves mentions to a knowledge base; neither identifies user intents nor extracts dates and locations from utterances. This pairing suits social-media monitoring or content enrichment, not the intent-and-entity extraction a chatbot requires.
- ✗
Custom text classification and key phrase extraction
Why it's wrong here
Custom text classification assigns whole-document labels, and key phrase extraction returns salient terms, neither of which resolves utterance intents or extracts typed entities such as dates and locations. This pairing suits document tagging and summarisation, not conversational understanding.
- ✗
Orchestration Workflow and custom text classification
Why it's wrong here
Orchestration Workflow coordinates multiple projects but does not itself classify intents, and custom text classification labels whole documents rather than extracting typed entities like dates and locations. This pairing suits routing between existing models, not building intent and entity recognition from scratch.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. 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.