AI-102 Implement generative AI solutions Practice Question
You need to create a chatbot that uses Azure OpenAI to answer questions about your company's internal policies. The responses must be based only on the provided policy documents. Which approach should you use?
⚠ Common exam trap
AI-102 often tests the misconception that fine-tuning 'teaches' a model new factual knowledge, when in reality fine-tuning shapes behavior and style while RAG is the correct pattern for grounding responses in specific, updatable documents.
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 Retrieval-Augmented Generation (RAG) with an Azure AI Search index of the documents.
RAG (Retrieval-Augmented Generation) is the correct approach because it grounds the model's responses in your actual policy documents by retrieving relevant chunks from an Azure AI Search index at query time and injecting them into the prompt. This ensures the chatbot answers only from the provided documents, avoids hallucination, and keeps the source of truth external and updatable without retraining. Azure OpenAI's 'On Your Data' feature implements exactly this pattern using Azure AI Search as the vector/keyword store.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use the model's pre-existing knowledge about common policies.
Why it's wrong here
The model's pre-existing knowledge is not restricted to the supplied policy documents, so answers may draw on unrelated or outdated content and cannot be grounded in the source. It is tempting because general knowledge suffices for open-domain chatbots where no document grounding is required.
- ✗
Fine-tune a GPT model on the policy documents.
Why it's wrong here
Fine-tuning bakes policy content into model weights, so responses are not grounded in the supplied documents and cannot cite them. It is tempting because fine-tuning adapts tone and format, and would suit teaching a consistent response style rather than document-grounded retrieval.
- ✗
Use prompt engineering to instruct the model to only use policy knowledge.
Why it's wrong here
Prompt instructions alone cannot guarantee grounding; the model may still answer from pre-trained knowledge, breaching the policy-only requirement. Prompt engineering suits controlling tone, format or reasoning style, and would be adequate where source fidelity is not mandated.
- ✓
Use Retrieval-Augmented Generation (RAG) with an Azure AI Search index of the documents.
Why this is correct
RAG retrieves relevant passages from an Azure AI Search index and grounds Azure OpenAI responses in those documents, satisfying the constraint that answers derive only from the supplied policy content rather than the model's pretrained knowledge.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.