The correct answer is to collect additional utterances that are similar to the confusing ones and retrain the model. This approach directly targets the root cause of poor intent classification accuracy in Azure AI Language CLU: ambiguous or overlapping training data between the 'ProductInquiry' and 'ReturnRequest' intents. By gathering more edge-case examples—such as “Can I send this back for a refund?” versus “Tell me about your return policy”—the model learns the subtle linguistic patterns that distinguish these intents, improving its ability to handle real-world customer queries. On the AI-102 exam, this scenario tests your understanding of how to refine a CLU project by focusing on high-ambiguity data rather than simply adding random samples, a common trap where candidates waste budget on generic utterances. A useful memory tip is “confuse the confusion”: when intents collide, collect more of what looks alike to sharpen the boundary.
AI-102 Plan and manage an Azure AI solution Practice Question
This AI-102 practice question tests your understanding of plan and manage an azure ai solution. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
You are a lead AI engineer for a global retail company. The company is building an AI-powered customer support chatbot using Microsoft Foundry. The chatbot must answer product questions, process returns, and escalate to human agents when needed. The solution uses Azure AI Language for intent recognition and Azure AI Bot Service for bot orchestration. During testing, the chatbot fails to understand customer queries about return policies. The intents 'ProductInquiry' and 'ReturnRequest' are defined, but the model often confuses them. You need to improve intent classification accuracy. The development team has already collected 500 sample utterances for each intent. You have a budget to collect additional data. What should you do?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Collect additional utterances that are similar to the confusing ones and retrain
Option B is correct because collecting additional utterances that are similar to the confusing ones directly addresses the ambiguity between the 'ProductInquiry' and 'ReturnRequest' intents. By providing more representative examples of edge cases where the intents overlap, the Azure AI Language model can better learn the subtle linguistic patterns that distinguish them, thereby improving classification accuracy without requiring a complete retraining from scratch.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
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 Azure AI Translator to translate utterances into multiple languages
Why it's wrong here
Does not address confusion between intents.
✓
Collect additional utterances that are similar to the confusing ones and retrain
Why this is correct
Adds more examples to differentiate intents.
Related concept
Read the scenario before looking for a memorised answer.
✗
Increase the confidence threshold in the bot configuration
Why it's wrong here
May cause false rejections but does not improve model.
✗
Create a new custom language project and retrain from scratch
Why it's wrong here
Wastes existing data and time.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often assume increasing the confidence threshold (Option C) will fix misclassifications, but this only adjusts the prediction cutoff and does not improve the underlying model's ability to differentiate intents, which is a data quality issue, not a threshold tuning issue.
Trap categories for this question
Similar concept trap
Does not address confusion between intents.
Detailed technical explanation
How to think about this question
Azure AI Language's custom text classification uses a transformer-based model that learns decision boundaries from training examples. When two intents share similar vocabulary (e.g., 'I want to return a product' vs. 'Tell me about this product'), the model's confusion stems from overlapping feature spaces. Adding more utterances that are semantically close to the decision boundary forces the model to learn finer-grained distinctions, effectively 'hardening' the boundary through additional gradient updates during retraining. This is analogous to active learning strategies where the model benefits most from examples near the classification margin.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Plan and manage an Azure AI solution — This question tests Plan and manage an Azure AI solution — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Collect additional utterances that are similar to the confusing ones and retrain — Option B is correct because collecting additional utterances that are similar to the confusing ones directly addresses the ambiguity between the 'ProductInquiry' and 'ReturnRequest' intents. By providing more representative examples of edge cases where the intents overlap, the Azure AI Language model can better learn the subtle linguistic patterns that distinguish them, thereby improving classification accuracy without requiring a complete retraining from scratch.
What should I do if I get this AI-102 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.