AI-900 Practice Question: Describe features of generative AI workloads on Azure
A developer is using Azure OpenAI to generate creative product descriptions. The outputs are often repetitive and lack variety. The developer wants to increase the diversity of the generated text while still keeping it coherent. Which parameter should the developer increase?
⚠ Common exam trap
Watch out — candidates often confuse temperature with frequency_penalty, thinking that penalizing repeated words (frequency_penalty) is the primary way to increase diversity, when in fact temperature directly controls the randomness of token selection.
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
✓
Temperature
Increasing the temperature parameter makes the model's output more random by amplifying the probability of less likely tokens, which increases diversity and reduces repetition. A higher temperature (e.g., 0.9) flattens the probability distribution, allowing the model to choose more varied words while still maintaining coherence, as long as the temperature is not set too high (e.g., above 1.0).
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Temperature
Why this is correct
In Azure OpenAI, temperature controls the probability distribution used for token sampling: increasing it flattens the distribution, making lower-probability tokens more likely and thereby producing more diverse, less repetitive creative product descriptions. This is the standard 'creativity' knob and the only option here that directly reweights token probabilities. For varied marketing copy, raising temperature (e.g., from 0.7 to 0.9) is the correct adjustment.
- ✗
Top_p
Why it's wrong here
Top_p (nucleus sampling) changes the candidate set by including tokens whose cumulative probability reaches a threshold, so raising it allows more uncommon tokens into the pool. This can add diversity, but it does not change the relative probabilities of tokens inside that set the way temperature does. In practice, top_p is often tuned alongside temperature, so it is not the primary or most direct control for increasing creativity in this scenario.
- ✗
Max_tokens
Why it's wrong here
Max_tokens specifies an upper limit on the number of tokens generated in the response, effectively capping length. It has no influence on which words or phrases are selected; a higher max_tokens simply allows a longer product description, not a more creative one. This parameter is unrelated to randomness or repetitiveness, so it cannot achieve the desired increase in diversity.
- ✗
Frequency_penalty
Why it's wrong here
Frequency_penalty reduces the likelihood of using a token based on how many times it has already appeared in the output, actively pushing the model away from exact word repetition. While this can make text feel less repetitive, it does not broaden the range of ideas or synonyms and can even change meaning if overapplied. Creativity is more directly governed by temperature, which shapes the entire sampling distribution rather than only penalizing repeats.
Go deeper
Related to this question
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.