AI-900 Practice Question: Describe features of generative AI workloads on Azure
A writer uses Azure OpenAI Service to generate story ideas. The current configuration uses a temperature setting of 0, causing the model to produce identical outputs for the same prompt. The writer wants more creative and diverse outputs. Which parameter should be increased?
⚠ Common exam trap
Many candidates confuse temperature with top_p, thinking both are equally responsible for randomness, but temperature is the direct control for randomness while top_p is an alternative sampling method that can also affect diversity but is not the parameter to increase for more creative outputs.
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
Temperature controls the randomness of the model's output. A temperature of 0 makes the model deterministic, always choosing the most likely next token, which leads to identical outputs for the same prompt. Increasing the temperature (e.g., to 0.7 or higher) introduces more randomness, allowing the model to sample from less likely tokens and produce more creative, diverse story ideas.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
max_tokens
Why it's wrong here
max_tokens is a hard limit on the number of tokens the model can emit before stopping, effectively controlling response length and preventing overly long output. It is a resource and validation constraint, not a sampling parameter, so it has no influence on the probability distribution that determines creativity. Raising max_tokens only lets the model continue longer, but it will not make the story ideas more inventive or diverse.
When this WOULD be correct
A question where the model's output is being cut off mid-sentence or is too short, and the requirement is to allow longer completions. For example: 'The model stops generating before finishing the story. Which parameter should be increased?'
- ✓
temperature
Why this is correct
In Azure OpenAI, temperature scales the logits (raw prediction scores) before the softmax layer, altering the probability distribution over the next token. Higher values, such as 0.8, flatten that distribution, making previously unlikely tokens much more probable, which encourages novel and varied story ideas. Lower values make sampling more deterministic and repetitive, so temperature is the standard parameter to directly increase creative randomness.
- ✗
top_p
Why it's wrong here
Top-p, or nucleus sampling, dynamically selects the smallest set of tokens whose cumulative probability exceeds a threshold like 0.9, then samples only from that subset. Lower top-p values make the output more focused and predictable, while higher values allow more low-probability tokens a chance. Although this can increase diversity, it does not uniformly scale all probabilities like temperature; it only truncates the tail of the distribution, so temperature is the more direct choice for boosting creative randomness.
When this WOULD be correct
A question states: 'The model outputs are too repetitive and include low-probability tokens. Which parameter should be adjusted to limit the set of tokens considered to those with the highest cumulative probability?' In that case, increasing top_p (e.g., to 0.9) would be correct.
- ✗
frequency_penalty
Why it's wrong here
Frequency penalty subtracts a value proportional to how many times a token has already appeared in the generated response, decreasing its chance of being sampled again. This curbs redundancy and encourages a broader vocabulary, but it operates only on token repetition, not on the global creativity or originality of the narrative. It does not increase the probability of novel concepts or unexpected plot turns the way raising temperature does.
When this WOULD be correct
A question asks: 'The model is generating repetitive phrases within a single response. Which parameter should be increased to penalize frequently used tokens and encourage more varied word choices?' In that scenario, frequency_penalty would be the correct answer.
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.
✓temperatureCorrect answer▾
Why this is correct
In Azure OpenAI, temperature scales the logits (raw prediction scores) before the softmax layer, altering the probability distribution over the next token. Higher values, such as 0.8, flatten that distribution, making previously unlikely tokens much more probable, which encourages novel and varied story ideas. Lower values make sampling more deterministic and repetitive, so temperature is the standard parameter to directly increase creative randomness.
✗max_tokensWrong answer — click to see why▾
Why this is wrong here
Increasing max_tokens only extends the length of the output, not its creativity or diversity. The writer's issue is that outputs are identical for the same prompt, which is controlled by temperature, not token limit.
★ When this WOULD be the correct answer
A question where the model's output is being cut off mid-sentence or is too short, and the requirement is to allow longer completions. For example: 'The model stops generating before finishing the story. Which parameter should be increased?'
Why candidates choose this
Candidates may think that more tokens allow the model to generate more ideas, but token count does not affect randomness or repetition of outputs.
✗top_pWrong answer — click to see why▾
Why this is wrong here
Top_p controls nucleus sampling, which limits the cumulative probability of token choices. While it can increase diversity, the question specifically asks for a parameter to increase creativity when temperature is 0; increasing top_p from 0 has no effect because temperature=0 forces greedy decoding regardless of top_p.
★ When this WOULD be the correct answer
A question states: 'The model outputs are too repetitive and include low-probability tokens. Which parameter should be adjusted to limit the set of tokens considered to those with the highest cumulative probability?' In that case, increasing top_p (e.g., to 0.9) would be correct.
Why candidates choose this
Candidates may confuse top_p with temperature as both control output randomness, and they might think adjusting top_p is an alternative way to increase diversity without understanding that temperature=0 overrides top_p.
✗frequency_penaltyWrong answer — click to see why▾
Why this is wrong here
Increasing frequency_penalty reduces repetition of tokens based on their frequency in the generated text, but it does not directly control the randomness or diversity of outputs. For making outputs more creative and diverse, temperature is the correct parameter to adjust.
★ When this WOULD be the correct answer
A question asks: 'The model is generating repetitive phrases within a single response. Which parameter should be increased to penalize frequently used tokens and encourage more varied word choices?' In that scenario, frequency_penalty would be the correct answer.
Why candidates choose this
Candidates may confuse frequency_penalty with temperature, thinking that penalizing frequent tokens will increase diversity, but frequency_penalty targets repetition within a response rather than overall randomness across different prompts.
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
Token
A token is a digital or physical object that represents a set of permissions or access rights, used to verify identity or grant access in computer systems.
Key term
Azure OpenAI Service
Azure OpenAI Service is a cloud platform from Microsoft that lets developers use powerful artificial intelligence models, like GPT-4, to build applications that can understand and generate human-like text, code, images, and more.
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.