AI-900 Practice Question: Describe features of generative AI workloads on Azure
A game development studio uses Azure OpenAI Service to generate unique backstories for non-player characters (NPCs). They want the generated stories to be coherent and relevant to a given character class (e.g., warrior, mage) but also creative and varied. Which parameter should the studio adjust primarily to increase the creativity and variety of the generated text?
⚠ Common exam trap
Microsoft often tests the distinction between temperature and top_p, where candidates mistakenly think top_p is the primary creativity control, but temperature is the fundamental parameter for adjusting randomness and variety in text generation.
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
✓
Increase the temperature parameter
Increasing the temperature parameter makes the model's output more random by scaling the probability distribution over tokens, which encourages less likely word choices and thus increases creativity and variety in generated text. For the game studio, a higher temperature (e.g., 0.8–1.0) will produce more diverse and imaginative backstories for different character classes, while still maintaining coherence if not set too high.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Increase the temperature parameter
Why this is correct
Increasing the temperature parameter scales the probability distribution over the token vocabulary before sampling; higher values flatten the distribution, increasing entropy and making less likely tokens more probable. This produces more unpredictable and creative backstories, as the model is less anchored to the highest-probability continuation. It directly controls the randomness versus determinism trade-off, making it the standard lever for creative variety.
- ✗
Increase the top_p parameter
Why it's wrong here
Increasing top_p (nucleus sampling) expands the cumulative probability mass from which tokens are sampled, including more low-probability options, which can add diversity in some cases. However, temperature is the primary parameter for adjusting randomness and creativity; top_p is a secondary sampling strategy that interacts with temperature but does not directly or reliably increase creative variety on its own. The question specifically targets the most direct control, which is temperature.
When this WOULD be correct
A question asks: 'Which parameter should be adjusted to ensure the generated text avoids repetitive phrases while maintaining high coherence?' In that case, increasing frequency_penalty would be correct, not top_p.
- ✗
Increase the frequency_penalty parameter
Why it's wrong here
Increasing the frequency_penalty applies a punitive adjustment proportional to how often a token has already appeared, reducing the likelihood of repeating the same tokens. This helps mitigate repetitive loops but does not directly increase the overall creativity or variety among different backstory concepts; it mainly cleans up output style. Since the goal is to generate more varied backstories, this penalty is not the primary mechanism to adjust.
When this WOULD be correct
A scenario where the generated text is too repetitive, with phrases or words appearing too often, and the goal is to reduce repetition without significantly increasing randomness. For example, a chatbot that keeps using the same greetings or a story generator that repeats character names excessively would benefit from increasing frequency_penalty.
- ✗
Decrease the max_tokens parameter
Why it's wrong here
Decreasing max_tokens only caps the maximum number of tokens the model can generate, truncating the output if it would otherwise be longer. It does not alter the token selection probabilities or the diversity of the content, so the backstory would simply be shorter and could end abruptly. This parameter controls length, not creativity, and thus would not increase variety.
When this WOULD be correct
A question asks: 'To reduce the cost and latency of API calls while ensuring responses are concise, which parameter should be decreased?' In that context, decreasing max_tokens limits output length, lowering token usage and cost.
Option-by-option analysis
Why each answer is right or wrong
Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.
✓Increase the temperature parameterCorrect answer▾
Why this is correct
Increasing the temperature parameter scales the probability distribution over the token vocabulary before sampling; higher values flatten the distribution, increasing entropy and making less likely tokens more probable. This produces more unpredictable and creative backstories, as the model is less anchored to the highest-probability continuation. It directly controls the randomness versus determinism trade-off, making it the standard lever for creative variety.
✗Increase the top_p parameterWrong answer — click to see why▾
Why this is wrong here
Increasing top_p (nucleus sampling) also increases randomness, but it primarily controls the cumulative probability threshold for token selection, not the overall creativity. For maximizing creativity and variety, temperature is the more direct parameter.
★ When this WOULD be the correct answer
A question asks: 'Which parameter should be adjusted to ensure the generated text avoids repetitive phrases while maintaining high coherence?' In that case, increasing frequency_penalty would be correct, not top_p.
Why candidates choose this
Candidates may confuse top_p with temperature because both control randomness, and they might think adjusting the probability distribution is the best way to increase variety.
✗Increase the frequency_penalty parameterWrong answer — click to see why▾
Why this is wrong here
Increasing frequency_penalty reduces repetition by penalizing tokens that have already appeared, which can increase variety but does not directly control creativity or randomness. The question asks for the primary parameter to increase creativity and variety, which is temperature, as it directly scales the probability distribution for more random outputs.
★ When this WOULD be the correct answer
A scenario where the generated text is too repetitive, with phrases or words appearing too often, and the goal is to reduce repetition without significantly increasing randomness. For example, a chatbot that keeps using the same greetings or a story generator that repeats character names excessively would benefit from increasing frequency_penalty.
Why candidates choose this
Candidates may confuse frequency_penalty with temperature, thinking that penalizing frequent tokens will force the model to be more creative by avoiding common patterns, but they overlook that temperature is the direct control for randomness and creativity.
✗Decrease the max_tokens parameterWrong answer — click to see why▾
Why this is wrong here
Decreasing max_tokens limits the length of generated text, which reduces the amount of content available for creativity and variety, making stories shorter and less detailed.
★ When this WOULD be the correct answer
A question asks: 'To reduce the cost and latency of API calls while ensuring responses are concise, which parameter should be decreased?' In that context, decreasing max_tokens limits output length, lowering token usage and cost.
Why candidates choose this
Candidates may think that limiting output length forces the model to be more creative within a shorter space, or they confuse max_tokens with controlling output diversity.
Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”
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
One of 985 original AI-900 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-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.