AI-900 Practice Question: Describe features of generative AI workloads on Azure
What is 'Azure OpenAI on your data' and what does it enable?
⚠ Common exam trap
It's easy for candidates to confuse 'using your data for grounding' with 'training a custom model on your data,' leading them to incorrectly select Option A, even though Azure OpenAI on your data does not involve any model training or fine-tuning.
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
✓
A managed RAG feature that answers questions from your connected data sources without custom pipeline code
'Azure OpenAI on your data' is a managed Retrieval Augmented Generation (RAG) feature that allows you to connect Azure OpenAI models directly to your data sources (e.g., Azure Blob Storage, Azure Cosmos DB, or Azure AI Search) without writing custom orchestration code. It enables the model to ground its responses in your proprietary data, improving accuracy and relevance while reducing hallucinations.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Training a custom Azure OpenAI model exclusively on your proprietary data
Why it's wrong here
'On your data' does not involve modifying model weights or running a training job. It is a managed RAG capability that retrieves relevant chunks from your connected indexes and supplies them in the prompt at inference time, letting the model ground answers in your proprietary content. Fine-tuning a custom model is a separate Azure OpenAI offering that requires prepared training data and changes the underlying model.
- ✓
A managed RAG feature that answers questions from your connected data sources without custom pipeline code
Why this is correct
This is correct: 'On your data' is a managed RAG feature that connects Azure OpenAI to sources such as Azure Blob Storage, Azure AI Search, or uploaded files, then automatically chunks, indexes, and retrieves relevant content to ground responses. You write no custom orchestration code for retrieval or prompt assembly; the service handles it end-to-end and cites the retrieved documents in the answer.
- ✗
Restricting Azure OpenAI to only use data from your Azure subscription, blocking external knowledge
Why it's wrong here
This reverses the feature's purpose. 'On your data' is additive: it augments the model's requests with supplementary text from your connected sources, but it never disables the model's pre-existing trained knowledge. Data isolation within your Azure subscription is a compliance and security consideration, not what this feature does; the model can still draw on its general knowledge when your documents don't contain an answer.
- ✗
A billing option that charges based on the volume of your data processed rather than tokens
Why it's wrong here
This confuses billing with functional value. Azure OpenAI usage is always metered per token, including input prompts, output completions, and any retrieved content injected by 'on your data' — never by raw data volume. 'On your data' is a retrieval-augmented generation feature for document Q&A, not a separate pricing plan or billing meter.
Quick reference
Azure Blob Storage Tier Comparison
| Tier | Storage Cost | Retrieval Cost | Latency | Use Case |
|---|---|---|---|---|
| Hot | Highest | Lowest | Immediate | Active data, frequent reads |
| Cool | Lower | Higher | Immediate | Data accessed < once / month |
| Cold | Lower still | Higher | Immediate | Data accessed < once / quarter |
| Archive | Lowest | Highest + rehydration delay | Hours | Long-term compliance retention |
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
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.