AI-900 Practice Question: Describe features of generative AI workloads on Azure
A marketing team uses Azure OpenAI to generate product descriptions. They want the output to reflect their latest catalog and current pricing, not the model's general knowledge. Which technique should they use?
⚠ Common exam trap
Microsoft often tests the misconception that fine-tuning is the only way to inject new knowledge, but the trap here is that fine-tuning creates a static model, whereas RAG provides dynamic, up-to-date information without retraining.
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
✓
Retrieval Augmented Generation (RAG)
Retrieval Augmented Generation (RAG) is the correct technique because it allows the model to retrieve up-to-date information from an external knowledge base—such as the latest catalog and current pricing—and incorporate that data into the generated output. Unlike the model's static training data, RAG dynamically injects fresh, domain-specific content at inference time, ensuring accuracy and relevance without modifying the model itself.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Few-shot learning
Why it's wrong here
Few-shot learning conditions the model by including a few input-output examples directly in the prompt, steering tone, format, or task behavior. Because those examples are static text pasted at request time, the model never queries a live catalog or pricing database, so anything learned from the examples can be outdated and does not guarantee grounded, current output. It changes the model's behavior for the call, but not its access to external data.
- ✗
Fine-tuning
Why it's wrong here
Fine-tuning retrains the base model's weights on a curated dataset, which is computationally expensive and requires a training pipeline, validation, and versioning. For a marketing catalog whose products and prices change frequently, every update would require another training cycle, and the model can still hallucinate facts not represented in the training set. It bakes a snapshot of information into the model rather than retrieving live data at inference time, making it ill-suited to this scenario.
- ✓
Retrieval Augmented Generation (RAG)
Why this is correct
Retrieval Augmented Generation (RAG) combines a retriever, such as Azure AI Search or a vector index, with an Azure OpenAI model. At inference time, the retriever queries the live product catalog and pricing source, returns the most relevant chunks, and inserts them into the prompt as grounded context. The model then generates descriptions using that retrieved evidence, which keeps output current, reduces hallucination, and supports frequently changing data without retraining.
- ✗
Prompt engineering
Why it's wrong here
Prompt engineering is the practice of carefully designing instructions, examples, and formatting to elicit better responses from a frozen model. By itself it injects no live data: any product information placed in the prompt is static, manually supplied text that must be updated by code or a human, and the model still falls back on its fixed training knowledge for anything not included. It can complement RAG by shaping how retrieved context is used, but it cannot replace the retrieval step that grounds output in the current catalog.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Training data
Training data is a set of examples used to teach a machine learning model how to make predictions or decisions.
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
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 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.