Courseiva
Implement generative AI solutionsmediumMultiple ChoiceObjective-mapped

AI-102 Implement generative AI solutions Practice Question

You are developing a customer support chatbot using Azure OpenAI Service. The chatbot must only answer questions related to the company's product catalog and policies. You want to minimize the risk of the chatbot generating harmful or off-topic responses. Which approach should you use?

⚠ Common exam trap

It's easy for candidates to confuse content filtering parameters (temperature, top_p, max_tokens) with instruction-based control, assuming that reducing randomness or output length can prevent off-topic responses, when in fact only explicit system-level instructions can enforce domain constraints.

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 a system message that instructs the model to only answer product-related questions.

A system message sets the foundational behavior of the model by providing high-level instructions that guide all subsequent responses. By explicitly instructing the model to only answer product-related questions, you establish a clear boundary that minimizes off-topic or harmful outputs. This approach leverages the model's instruction-following capability, which is more effective than parameter tuning alone for content restriction.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Set the max_tokens parameter to 100.

    Why it's wrong here

    Max_tokens only limits response length, not topic.

  • Use a system message that instructs the model to only answer product-related questions.

    Why this is correct

    System messages define the assistant's behavior and constraints.

  • Set the temperature parameter to 0.

    Why it's wrong here

    Temperature controls randomness, not topic adherence.

  • Set the top_p parameter to 0.1.

    Why it's wrong here

    Top_p controls nucleus sampling, not topic restriction.

About these practice questions

Courseiva writes every AI-102 question from scratch — 945 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 →

How Courseiva writes practice questions · Editorial policy

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.