AI-900 Practice Question: Describe features of generative AI workloads on Azure
A customer service company uses Azure OpenAI Service to generate automated replies to customer inquiries. They want each reply to adopt a polite and empathetic tone. Which configuration should they use to guide the model's behavior without retraining?
⚠ Common exam trap
Watch out — candidates often confuse sampling parameters (temperature, top_p) with behavioral guidance, assuming they control tone, when in fact they only control randomness or diversity, not the specific style or persona of the response.
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
✓
Define a system message that instructs the model to be polite and empathetic.
A system message in Azure OpenAI Service allows you to set the context and tone for the model's responses without retraining. By defining a system message that instructs the model to be polite and empathetic, you guide the model's behavior at inference time, ensuring replies adopt the desired tone.
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 temperature parameter to a high value (e.g., 1.0).
Why it's wrong here
High temperature values increase the randomness of token sampling, which can make the model's responses more creative or unpredictable. However, this parameter does not encode any semantic instruction about how the assistant should behave, so it cannot guarantee politeness or empathy. In fact, setting temperature to 1.0 may lead to inconsistent replies that occasionally violate the desired tone, because the model is not being told to adopt that tone.
- ✗
Set the top_p parameter to a low value (e.g., 0.1).
Why it's wrong here
Low top_p values restrict the cumulative probability from which the model picks tokens, making output more focused and less diverse. While this can reduce wild or tangential responses, it is purely a sampling control and has no influence on the assistant's persona or conversational style. The model would need an explicit system-level directive to know it should be polite and empathetic, rather than simply speaking from a smaller vocabulary set.
- ✓
Define a system message that instructs the model to be polite and empathetic.
Why this is correct
The system message in the Chat Completions API is specifically designed to set the context and behavioral guidelines for the assistant before any user message is processed. By instructing the model to be polite and empathetic in that system prompt, you are directly shaping the tone and persona of every generated reply, which is exactly the intended mechanism for achieving a consistent customer-service demeanor. This is the correct answer because it provides the model with an explicit, high-level instruction that influences output style across all interactions.
- ✗
Set the max_tokens parameter to a specific value (e.g., 150).
Why it's wrong here
Max_tokens defines the upper limit of tokens the model can generate, serving solely as a cap on response length. It does not alter the semantic content, tone, or manner of the reply; even a short response can be curt or unempathetic if no behavioral instruction is given. Thus, while useful for controlling costs and response size, it cannot substitute for a system message that defines the assistant's desired attitude.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
Key term
Service
A service is a software component or system that performs a specific function and is available to be used by other programs or users over a network.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 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-900 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-900 exam.