Quick Answer
The answer is Option B because it correctly implements Retrieval-Augmented Generation (RAG) to ground Azure OpenAI outputs in verified legal data, directly solving the hallucination risk. By indexing past case summaries in Azure AI Search and using Azure Functions triggered by blob uploads, the solution retrieves relevant context before generating summaries, ensuring accuracy while maintaining a fully serverless architecture with minimal operational overhead. On the AI-102 exam, this scenario tests your understanding of how RAG mitigates model hallucination in domain-specific applications—a common trap is choosing Option A, which relies solely on system messages that cannot guarantee factual accuracy. Remember the key distinction: RAG retrieves real data to augment the prompt, whereas fine-tuning (Option C) or simple prompting (Option D) lacks this grounding. Memory tip: "RAG Retrieves Real Answers, Guaranteeing Groundedness."
This AI-102 practice question tests your understanding of implement generative ai solutions. 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. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. 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.
You are a cloud solution architect at a legal firm. The firm needs to automate the summarization of legal documents. They have a large corpus of past case summaries and legal documents stored in Azure Blob Storage. They want to use Azure OpenAI to generate summaries for new documents. The solution must ensure that the generated summaries are accurate and do not contain hallucinated legal facts. The firm also requires that the solution be serverless and minimize operational overhead. You need to design the solution.
Option A: Use Azure OpenAI with a system message that instructs the model to be accurate. Deploy the model as a web app on Azure App Service and call it from Azure Functions triggered by new blob uploads.
Option B: Use Azure OpenAI with Retrieval-Augmented Generation (RAG) by indexing the past case summaries in Azure AI Search. Use Azure Functions to process new documents, retrieve relevant cases, and pass them as context to the model. Store summaries in Azure Cosmos DB.
Option C: Fine-tune an Azure OpenAI model on the past case summaries and deploy it as a managed endpoint. Use Azure Logic Apps to trigger summarization when new blobs are added.
Option D: Use Azure OpenAI with the chat API and provide the entire document in the prompt. Use Azure Container Instances to run a service that calls the API and writes summaries back to Blob Storage.
Which option should you choose?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "minimum / minimize"
Why it matters: Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
Option B
RAG grounds responses in retrieved documents, reducing hallucination.
Option A
Why wrong: No retrieval leads to potential hallucinations.
Option D
Why wrong: Full document in prompt may exceed token limits and still hallucinate.
Option C
Why wrong: Fine-tuning does not eliminate hallucination and is costly.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Option B
Option B is correct because it uses Retrieval-Augmented Generation (RAG) with Azure AI Search to ground the model's output in verified past case summaries, directly addressing the requirement to avoid hallucinated legal facts. The serverless architecture is achieved via Azure Functions triggered by blob uploads, minimizing operational overhead, while storing summaries in Azure Cosmos DB provides a scalable, low-latency output store.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Option B
Why this is correct
RAG grounds responses in retrieved documents, reducing hallucination.
Clue confirmation
The clue word "minimum / minimize" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
Option A
Why it's wrong here
No retrieval leads to potential hallucinations.
Option D
Why it's wrong here
Full document in prompt may exceed token limits and still hallucinate.
Option C
Why it's wrong here
Fine-tuning does not eliminate hallucination and is costly.
Common exam traps
The trap here is that candidates may assume fine-tuning (Option C) or a simple system message (Option A) is sufficient to ensure factual accuracy, but Azure OpenAI models require grounded context via RAG to reliably avoid hallucination in domain-specific tasks like legal summarization.
Detailed technical explanation
RAG works by embedding the user query (or new document) and retrieving the top-k relevant chunks from Azure AI Search using vector or hybrid search, then injecting those chunks into the prompt as context. This grounds the model's response in actual data, reducing hallucination risk. Azure Functions with a Blob Storage trigger is inherently serverless, scaling to zero when idle, and Cosmos DB provides a globally distributed, low-latency store for the generated summaries.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
A media company stores terabytes of video archives that are accessed once a year for audit purposes. Moving these objects to a cold storage tier (Azure Archive, S3 Glacier, or Google Nearline) costs a fraction of hot storage. Questions like this test whether you understand storage tiers, access frequency tradeoffs, and retrieval latency requirements.
What to study next
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Implement generative AI solutions — study guide chapter
Learn the concepts, then practise the questions
Implement generative AI solutions practice questions
Targeted practice on this topic area only
All AI-102 questions
988 questions across all exam domains
Microsoft Azure AI Engineer Associate AI-102 study guide
Full concept coverage aligned to exam objectives
AI-102 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise AI-102 questions linked to Implement an agentic solution.
Practise AI-102 questions linked to Implement computer vision solutions.
Practise AI-102 questions linked to Implement knowledge mining and information extraction solutions.
Practise AI-102 questions linked to Implement image and video processing solutions.
Practise AI-102 questions linked to Implement natural language processing solutions.
Practise AI-102 questions linked to Implement generative AI solutions.
Practise AI-102 questions linked to Implement agentic AI solutions.
Practise AI-102 questions linked to Implement knowledge mining and document intelligence solutions.
Practise AI-102 questions linked to Plan and manage an Azure AI solution.
Practise AI-102 questions linked to Implement content moderation solutions.
Practise AI-102 questions linked to AI-102 fundamentals.
Practise AI-102 questions linked to AI-102 scenario.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Implement generative AI solutions — This question tests Implement generative AI solutions — Read the scenario before looking for a memorised answer..
The correct answer is: Option B — Option B is correct because it uses Retrieval-Augmented Generation (RAG) with Azure AI Search to ground the model's output in verified past case summaries, directly addressing the requirement to avoid hallucinated legal facts. The serverless architecture is achieved via Azure Functions triggered by blob uploads, minimizing operational overhead, while storing summaries in Azure Cosmos DB provides a scalable, low-latency output store.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Yes — watch for: "minimum / minimize". Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
Read the scenario before looking for a memorised answer.
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-102 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-102 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.