- A
Fine-tuning the model on the product catalog
Why wrong: Fine-tuning adjusts the model's weights using labeled data, but it does not dynamically retrieve current information from a database. The model may still hallucinate or use outdated information.
- B
Prompt engineering with retrieval augmented generation (RAG)
RAG retrieves relevant chunks from the vector database and adds them to the prompt, ensuring the model uses the latest, specific product details to generate accurate descriptions.
- C
Zero-shot prompting without additional data
Why wrong: Zero-shot prompting relies solely on the model's internal knowledge, which may be generic or outdated, leading to inaccuracies for the specific product catalog.
- D
Reinforcement learning from human feedback (RLHF)
Why wrong: RLHF aligns the model with human preferences through reward signals, but it does not provide a mechanism to retrieve and use live product data from a database.
AI-900 Practice Question: Describe features of generative AI workloads on Azure
This AI-900 practice question tests your understanding of describe features of generative ai workloads on azure. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. A key principle to apply: rAG dynamically retrieves external information to augment prompts.. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A marketing agency wants to use Azure OpenAI Service to generate product descriptions. They need the descriptions to be factually accurate and based on their specific product catalog, which is stored in a vector database. Which technique should they use to ground the model's outputs in their own data?
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
Prompt engineering with retrieval augmented generation (RAG)
Retrieval augmented generation (RAG) is the correct technique because it allows the model to retrieve relevant, up-to-date product information from the vector database at inference time and use that data as context to generate factually accurate descriptions. This grounds the model's outputs in the specific product catalog without modifying the underlying model weights, ensuring responses are based on the agency's own data.
Key principle: RAG dynamically retrieves external information to augment prompts.
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 the product catalog
Why it's wrong here
Fine-tuning adjusts the model's weights using labeled data, but it does not dynamically retrieve current information from a database. The model may still hallucinate or use outdated information.
- ✓
Prompt engineering with retrieval augmented generation (RAG)
Why this is correct
RAG retrieves relevant chunks from the vector database and adds them to the prompt, ensuring the model uses the latest, specific product details to generate accurate descriptions.
Related concept
RAG dynamically retrieves external information to augment prompts.
- ✗
Zero-shot prompting without additional data
Why it's wrong here
Zero-shot prompting relies solely on the model's internal knowledge, which may be generic or outdated, leading to inaccuracies for the specific product catalog.
- ✗
Reinforcement learning from human feedback (RLHF)
Why it's wrong here
RLHF aligns the model with human preferences through reward signals, but it does not provide a mechanism to retrieve and use live product data from a database.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often confuse fine-tuning with RAG, assuming that training the model on custom data is the only way to incorporate proprietary information, but RAG achieves the same goal more efficiently and flexibly without retraining.
Detailed technical explanation
How to think about this question
RAG works by embedding the user query into a vector, performing a similarity search against the vector database (e.g., using cosine similarity or Euclidean distance), and then prepending the retrieved text chunks as context in the prompt sent to the Azure OpenAI model. This approach leverages the model's in-context learning ability without altering its parameters, making it ideal for scenarios where data changes frequently, such as a marketing agency's evolving product catalog. A subtle behavior is that the quality of the generated description heavily depends on the chunking strategy and embedding model used to index the catalog.
KKey Concepts to Remember
- RAG dynamically retrieves external information to augment prompts.
- RAG helps ground LLMs in specific, up-to-date data sources.
- Vector databases are commonly used with RAG for efficient semantic search.
- RAG reduces model hallucination by providing factual context.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
RAG dynamically retrieves external information to augment prompts.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. RAG dynamically retrieves external information to augment prompts. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Review rAG dynamically retrieves external information to augment prompts., then practise related AI-900 questions on the same topic to reinforce the concept.
- →
Describe features of generative AI workloads on Azure — study guide chapter
Learn the concepts, then practise the questions
- →
Describe features of generative AI workloads on Azure practice questions
Targeted practice on this topic area only
- →
All AI-900 questions
1,020 questions across all exam domains
- →
Microsoft Azure AI Fundamentals AI-900 study guide
Full concept coverage aligned to exam objectives
- →
AI-900 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AI-900 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Describe Artificial Intelligence workloads and considerations practice questions
Practise AI-900 questions linked to Describe Artificial Intelligence workloads and considerations.
Describe fundamental principles of machine learning on Azure practice questions
Practise AI-900 questions linked to Describe fundamental principles of machine learning on Azure.
Describe features of computer vision workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of computer vision workloads on Azure.
Describe features of Natural Language Processing workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of Natural Language Processing workloads on Azure.
Describe features of generative AI workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of generative AI workloads on Azure.
AI-900 fundamentals practice questions
Practise AI-900 questions linked to AI-900 fundamentals.
AI-900 scenario practice questions
Practise AI-900 questions linked to AI-900 scenario.
AI-900 troubleshooting practice questions
Practise AI-900 questions linked to AI-900 troubleshooting.
Practice this exam
Start a free AI-900 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AI-900 question test?
Describe features of generative AI workloads on Azure — This question tests Describe features of generative AI workloads on Azure — RAG dynamically retrieves external information to augment prompts..
What is the correct answer to this question?
The correct answer is: Prompt engineering with retrieval augmented generation (RAG) — Retrieval augmented generation (RAG) is the correct technique because it allows the model to retrieve relevant, up-to-date product information from the vector database at inference time and use that data as context to generate factually accurate descriptions. This grounds the model's outputs in the specific product catalog without modifying the underlying model weights, ensuring responses are based on the agency's own data.
What should I do if I get this AI-900 question wrong?
Review rAG dynamically retrieves external information to augment prompts., then practise related AI-900 questions on the same topic to reinforce the concept.
What is the key concept behind this question?
RAG dynamically retrieves external information to augment prompts.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 11, 2026
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.