AI-102 Practice Question: Implement natural language processing solutions
You are designing a solution that uses Azure AI Language's conversational language understanding (CLU) to interpret user requests in a banking app. The app must handle utterances like 'Transfer $500 from savings to checking' and extract the amount, source account, and destination account. Which two actions should you perform when creating the CLU project? (Choose two.)
⚠ Common exam trap
The trap here is thinking that prebuilt entities can replace custom entity definitions for domain-specific extraction, when they lack the context to distinguish between similar numeric values.
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
✓
Create entities for 'Amount', 'SourceAccount', and 'DestinationAccount'.
To correctly interpret the banking utterances, you must define intents to capture the user's goal and entities to extract the specific data fields. Intents like 'TransferMoney' and entities for 'Amount', 'SourceAccount', and 'DestinationAccount' are fundamental. Prebuilt entities alone lack specificity, and custom training is required.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Create entities for 'Amount', 'SourceAccount', and 'DestinationAccount'.
Why this is correct
Entities are used to extract specific pieces of information from utterances. In this scenario, extracting the amount, source account, and destination account is crucial for executing the transfer. Defining these entities with appropriate labels enables the model to identify and return them in the response.
- ✗
Train the model using only the default training set provided by Azure.
Why it's wrong here
CLU requires custom training with domain-specific utterances. The default training set is generic and would not accurately interpret banking-specific language. Training with labeled examples that include the specific entities and intents is necessary for the model to perform well on the banking app's utterances.
- ✗
Add a prebuilt entity for 'Number' to automatically extract the amount.
Why it's wrong here
While a prebuilt entity for 'Number' could extract numeric values, it would not distinguish between amount and other numbers (like account numbers). The scenario requires specific extraction of 'Amount' as a distinct entity. Relying solely on a prebuilt entity would not provide the necessary granularity and could lead to incorrect extraction.
- ✓
Define intents such as 'TransferMoney' and 'CheckBalance'.
Why this is correct
Defining intents is essential in CLU to categorize the user's goal. For the banking app, an intent like 'TransferMoney' would capture the action of transferring funds. This allows the model to route the utterance to the appropriate handling logic. Without intents, the system cannot determine what the user wants to do.
- ✗
Configure the project to use multiple languages for utterance interpretation.
Why it's wrong here
The scenario does not mention multilingual requirements. Adding multiple languages would increase complexity and is not needed for the banking app if it only serves English-speaking users. This action is irrelevant to the core requirement of extracting amount and account information from English utterances.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.