AI-102 Implement an agentic solution Practice Question
A company wants to build a customer support agent using Microsoft Copilot Studio. The agent needs to understand natural language and handle complex queries beyond simple keyword matching. The agent should be able to escalate to a human agent when it cannot resolve the issue. Which feature should the agent use to understand natural language?
⚠ Common exam trap
Candidates often confuse entity extraction (Option D) or topic triggers (Option C) with true natural language understanding, not realizing that generative answers powered by LLMs are required for handling complex, unconstrained queries beyond simple keyword matching.
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
✓
Enable generative answers and configure a knowledge source.
Generative answers in Microsoft Copilot Studio use large language models (LLMs) to interpret natural language queries and generate responses based on configured knowledge sources (e.g., SharePoint, websites, or custom data). This enables the agent to handle complex, conversational queries beyond simple keyword matching, and it can escalate to a human agent when confidence is low or the issue cannot be resolved.
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 a Power Automate flow to process queries.
Why it's wrong here
A Power Automate flow executes backend actions and integrations; it does not parse user language or determine intent. It is tempting because flows handle escalation and system calls, but natural language understanding must come from the agent's NLU engine, with the flow invoked afterwards.
- ✓
Enable generative answers and configure a knowledge source.
Why this is correct
Generative answers with a configured knowledge source let the agent use large language models to interpret intent and retrieve relevant content, handling complex queries beyond keyword matching. This satisfies the natural language understanding requirement, and escalation can be added separately.
- ✗
Create topics with trigger phrases.
Why it's wrong here
Trigger phrases match topics through keyword-style recognition, so paraphrased or complex queries fail to route correctly. Topics are tempting because they define conversation paths, but the scenario explicitly requires understanding beyond keyword matching, which the NLU model provides.
- ✗
Use entities to extract key information.
Why it's wrong here
Entities extract structured values such as dates or order numbers from utterances; they do not interpret overall intent or handle complex phrasing. Entities are tempting because they capture specific data, but natural language understanding across varied queries requires the agent's NLU model, not slot extraction alone.
Visual reference
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 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.