AI-900 Practice Question: Describe features of generative AI workloads on Azure
A company wants to use Azure OpenAI Service to generate product descriptions. They need to ensure the model's output is based on their specific product catalog and pricing, not on generic information. Which approach should they use?
⚠ Common exam trap
Candidates often confuse fine-tuning (A) as the only way to inject custom data, overlooking that RAG is more practical for dynamic, large-scale, or frequently updated knowledge bases 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
✓
Implementing Retrieval Augmented Generation (RAG) with their catalog.
Retrieval Augmented Generation (RAG) allows the model to dynamically retrieve relevant product catalog and pricing information from an external knowledge base at inference time, ensuring the generated descriptions are grounded in the company's specific data rather than relying on the model's generic training data. This approach avoids the need for costly fine-tuning and keeps the output up-to-date without retraining.
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-tuning the model on their product catalog.
Why it's wrong here
Fine-tuning modifies the model's underlying weights through supervised training on product-description pairs, which can improve tone and style but requires a full retraining cycle whenever the catalog changes. This approach cannot keep pace with dynamic inventories unless you repeatedly retrain, and it risks overfitting or outdated factuality for new or updated products. Thus it is too rigid and costly for a continuously evolving product catalog.
- ✗
Using few-shot learning with examples.
Why it's wrong here
Few-shot learning inserts a small number of example product-description pairs directly into the prompt to guide the model's output format, but the prompt's limited context window means you can only show a tiny fraction of the catalog. For a specific product not covered by those examples, the model has no access to its actual details, so it may pattern-match to the examples and generate plausible but incorrect content. This approach does not scale to a large catalog and does not guarantee grounding for unseen items.
- ✓
Implementing Retrieval Augmented Generation (RAG) with their catalog.
Why this is correct
RAG (Retrieval Augmented Generation) pairs a retrieval system, such as a vector index over the product catalog, with the language model, so at inference time the most relevant product records are retrieved and added to the prompt as grounded context. This allows the model to generate descriptions based on actual, current catalog data without any weight updates, making it immediately responsive to product additions or changes. It scales efficiently to thousands of products and reduces hallucination by constraining generation to the retrieved evidence.
- ✗
Increasing the temperature parameter.
Why it's wrong here
Temperature is a sampling parameter that controls the randomness of token selection: a higher temperature produces more varied, creative phrasing, while a lower temperature makes outputs more deterministic and focused. It does not inject any external data or product facts, so changing it cannot make the model aware of the catalog's contents. Setting temperature high would only introduce verbose or unpredictable wording, not improve the factual applicability of the descriptions.
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
Retrieval augmented generation
Retrieval augmented generation (RAG) is a technique that combines information retrieval with text generation to produce more accurate and contextually relevant answers.
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.