AI-900 Practice Question: Describe features of generative AI workloads on Azure
A support team wants its generative AI chat solution on Azure to answer questions using only the company's internal HR policy documents, and to cite the exact source page for every answer. They want to minimize custom code. Which Azure feature should they use?
⚠ Common exam trap
The trap here is assuming that fine-tuning is the way to teach a model private facts, when retrieval-based grounding is what actually supplies and cites source 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
✓
Azure AI Search with the integrated vectorization and 'On Your Data' connection in Azure OpenAI Service
Grounding a model in a specific document set is done by retrieving relevant chunks at query time and passing them to the model, which is exactly what the On Your Data pattern with Azure AI Search provides. It returns citations to the source content and requires only configuration, satisfying both the accuracy and low-effort requirements.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increasing the model's temperature setting so it explores the HR documents more thoroughly
Why it's wrong here
Temperature controls randomness in token selection; it has no mechanism for reading documents or citing pages. Raising it would make responses less predictable and more prone to invented details, which directly conflicts with the requirement for grounded, citable answers.
- ✓
Azure AI Search with the integrated vectorization and 'On Your Data' connection in Azure OpenAI Service
Why this is correct
Connecting Azure OpenAI to your own indexed data lets the model ground answers in the HR documents and return citations, with minimal custom code. Integrated vectorization handles embedding generation and chunking, so the team configures a data source rather than building a retrieval pipeline.
- ✗
Fine-tuning a base GPT model with the HR policy documents uploaded as a JSONL training file
Why it's wrong here
Fine-tuning changes the model's behavior and style, but it does not reliably store or cite specific source documents, and citations are not produced from training data. It also requires a formatted training set and periodic retraining when policies change, which is far more effort than the team wants.
- ✗
Deploying the model with a larger max tokens response limit to fit whole policy sections in the reply
Why it's wrong here
The max tokens parameter only caps how long a completion can be. It does not give the model access to the HR documents or produce citations, so a longer answer would still be generated from the model's general training rather than the company's policies.
Go deeper
Related to this question
Learn chapter
System Messages and Grounding Prompts
Key term
Generative AI
Generative AI is a type of artificial intelligence that creates new content—like text, images, or code—by learning patterns from existing data.
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
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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.