AI-900 Practice Question: Describe features of generative AI workloads on Azure
A company wants to build a chatbot that can answer questions based on its internal policy documents. The documents are stored in Azure Blob Storage. They plan to use Azure OpenAI to generate answers. Which approach should they use to ensure the answers are grounded in the actual policy content?
⚠ Common exam trap
A common mix-up: candidates confuse fine-tuning (Option A) with retrieval-augmented generation, assuming that training the model on the data is the only way to ground answers, when in fact RAG provides a more flexible and cost-effective solution for dynamic or large document sets.
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 Azure AI Search to index the documents and provide relevant passages as context to GPT-4
Azure AI Search can index the policy documents stored in Azure Blob Storage, enabling retrieval of relevant passages based on the user's query. These passages are then provided as context in the prompt to GPT-4, ensuring the generated answer is grounded in the actual policy content rather than relying on the model's pre-trained knowledge.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Fine-tune GPT-4 on all policy documents
Why it's wrong here
Fine-tuning GPT-4 over the policy corpus modifies the model's internal weights via supervised learning, which is compute-intensive, prone to catastrophic forgetting of other capabilities, and must be redone whenever policies change. It also gives the model memorized, approximate answers rather than retrieving exact passages, so it can hallucinate or cite outdated text — exactly what a policy QA system cannot afford.
- ✓
Use Azure AI Search to index the documents and provide relevant passages as context to GPT-4
Why this is correct
Azure AI Search builds a searchable index over the policy documents, and at runtime the user's question retrieves the top-ranked relevant passages (via keyword, semantic, or vector search) which are then inserted as grounding context into the GPT-4 prompt. This retrieval-augmented generation (RAG) pattern lets GPT-4 base its answer on actual policy text, reducing hallucinations, and lets you add or update documents simply by re-indexing — no retraining or weight updates needed.
- ✗
Include the entire policy document text in the prompt each time
Why it's wrong here
Simply concatenating every policy document into the prompt is infeasible for large knowledge bases because GPT-4's context window is finite — a single long policy manual can already exceed the token limit, let alone multiple documents. Even when the text fits, doing this per question wastes tokens, increases latency and cost, and buries the relevant passage in noise, which causes the model to give less precise answers. The proper design is to retrieve only the pertinent fragments.
- ✗
Use DALL-E to visualize policy concepts
Why it's wrong here
DALL-E is a text-to-image generative model that has no capacity to parse or reason about policy text; it outputs image pixels, not answers to questions. Asking it to 'visualize policy concepts' would produce artistic illustrations that cannot be verified against the source documentation and would fail to satisfy the user's need for a grounded textual answer. Therefore it addresses a different modality entirely and is unrelated to the retrieval problem.
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
Azure AI Search
Azure AI Search is a cloud search service that uses artificial intelligence to index and search through large amounts of data, returning relevant results that feel as smart as a Google search.
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
About these practice questions
This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam 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.