AI-900 Practice Question: Describe features of generative AI workloads on Azure
A company uses Azure OpenAI Service to generate executive summaries of lengthy reports. The generated summaries sometimes include information that was not present in the original report, making them unreliable. Which Azure OpenAI Service feature should the company use to anchor the model to the provided report content?
⚠ Common exam trap
Many candidates think a system message or parameter adjustment can reliably enforce content grounding, but only the 'Add your data' feature provides a technical mechanism to restrict the model's knowledge to the provided documents.
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
✓
Use the 'Add your data' feature (also known as 'Azure OpenAI on your data')
The 'Add your data' feature (Azure OpenAI on your data) allows the model to ground its responses in the specific content you provide, such as the original report. This prevents the model from generating information not present in the source, addressing the hallucination issue directly by restricting the model's knowledge base to the uploaded documents.
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 it's wrong here
Increasing the temperature parameter adjusts the softmax sampling distribution, making token selection more random and diverse. While lower temperatures encourage more deterministic, focused outputs, higher temperatures do not tie the model to any external data source—they can actually increase the likelihood of drifting away from factual content and hallucinating. Temperature only controls creative variability, never grounding.
When this WOULD be correct
A question asks how to make the model generate more diverse or creative responses, such as for brainstorming or story generation, where higher temperature is desired.
- ✗
Increase the frequency_penalty parameter
Why it's wrong here
The frequency_penalty parameter applies a penalty proportional to how often a token has already appeared in the generated sequence, which reduces immediate repetition and n-gram loops. It does not change the model's underlying knowledge or provide access to authoritative documents, so the model can still confidently fabricate details. This parameter shapes output style (fluency and diversity), not the truthfulness or grounding of the content.
When this WOULD be correct
If the question were about reducing repetitive or redundant phrases in generated text, such as in a summarization task where the model keeps repeating the same points, increasing frequency_penalty would be correct.
- ✗
Use the system message to instruct the model to only use provided content
Why it's wrong here
A system message can guide behavior but is a soft instruction. The model may still ignore it, especially for longer or complex queries. It does not mechanically restrict the model to use only supplied data.
When this WOULD be correct
If the question were about guiding the model's behavior or tone without needing strict grounding to external data, such as 'A company wants the model to always respond politely and concisely. Which feature should they use?' then the system message would be correct.
- ✓
Use the 'Add your data' feature (also known as 'Azure OpenAI on your data')
Why this is correct
This feature enables you to connect your own data sources to the model. The model then retrieves relevant information from your data to generate responses, significantly reducing hallucinations and ensuring the output is based on the provided content.
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.
✓Use the 'Add your data' feature (also known as 'Azure OpenAI on your data')Correct answer▾
Why this is correct
This feature enables you to connect your own data sources to the model. The model then retrieves relevant information from your data to generate responses, significantly reducing hallucinations and ensuring the output is based on the provided content.
✗Increase the temperature parameterWrong answer — click to see why▾
Why this is wrong here
Increasing the temperature parameter makes the model more creative and random, which would increase the likelihood of generating content not in the original report, not reduce it.
★ When this WOULD be the correct answer
A question asks how to make the model generate more diverse or creative responses, such as for brainstorming or story generation, where higher temperature is desired.
Why candidates choose this
Candidates may think temperature controls adherence to input, but it actually controls randomness; they confuse it with a 'strictness' setting.
✗Increase the frequency_penalty parameterWrong answer — click to see why▾
Why this is wrong here
Increasing frequency_penalty reduces repetition of tokens, but does not prevent the model from generating information not present in the provided content. It does not anchor the model to the source material.
★ When this WOULD be the correct answer
If the question were about reducing repetitive or redundant phrases in generated text, such as in a summarization task where the model keeps repeating the same points, increasing frequency_penalty would be correct.
Why candidates choose this
Candidates may confuse frequency_penalty with a mechanism to enforce faithfulness to input, not realizing it only penalizes token repetition, not hallucination.
✗Use the system message to instruct the model to only use provided contentWrong answer — click to see why▾
Why this is wrong here
The system message can instruct the model, but it does not guarantee grounding to the provided content; the model may still hallucinate or fabricate information not in the source. The 'Add your data' feature is required to restrict the model to use only the provided data.
★ When this WOULD be the correct answer
If the question were about guiding the model's behavior or tone without needing strict grounding to external data, such as 'A company wants the model to always respond politely and concisely. Which feature should they use?' then the system message would be correct.
Why candidates choose this
Candidates may think that a clear instruction in the system message is sufficient to prevent hallucination, underestimating the model's tendency to generate plausible but incorrect information when not explicitly grounded to a data source.
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
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.
Key term
Feature
A feature is a distinct unit of functionality that delivers value to the user, often managed and tracked throughout the software development lifecycle.
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.