AI-102 Implement generative AI solutions Practice Question
You are building a solution to generate product descriptions using Azure OpenAI Service. You need to ensure that the output adheres to a specific tone (professional, friendly) and length (50-100 words). Which parameter should you adjust?
⚠ Common exam trap
Many exam-takers confuse parameters that control output randomness (temperature, top_p) or length (max_tokens) with the system message's role in defining qualitative constraints like tone and style, leading them to select A or D instead of C.
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
✓
Set the system message with instructions about tone and length.
The system message in Azure OpenAI Service is specifically designed to set the overall behavior and context for the model, including tone and length constraints. By providing instructions like 'Respond in a professional and friendly tone, and keep the output between 50 and 100 words,' the model will adhere to these guidelines throughout the conversation. This is the primary mechanism for controlling qualitative aspects of the output, as opposed to parameters that control randomness or token limits.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Configure max_tokens to limit response length.
Why it's wrong here
max_tokens caps the number of generated tokens, which limits length but cannot enforce a 50-100 word range or a professional, friendly tone. It is the right parameter for hard truncation or cost control, which is why it looks relevant to the length requirement.
- ✗
Modify the top_p parameter.
Why it's wrong here
Top_p affects diversity of output, not tone/length.
- ✓
Set the system message with instructions about tone and length.
Why this is correct
The system message sets persistent behavioural instructions applied before user turns, so tone and word-count guidance there governs every generated description. Prompt-level parameters such as temperature or max_tokens cannot reliably enforce a professional-friendly tone or a 50-100 word range.
- ✗
Adjust the temperature parameter.
Why it's wrong here
Temperature controls sampling randomness, not tone or word count, so it cannot enforce a 50-100 word professional or friendly output. It is the right parameter when you want creative variation or deterministic responses, which is why it seems relevant to output shaping.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.