AI-102 Implement generative AI solutions Practice Question
You are building a generative AI application using Azure OpenAI Service. The application must provide factual answers based on your company's internal knowledge base. You need to minimize the risk of the model generating incorrect information (hallucinations). Which approach should you take?
⚠ Common exam trap
The AI-102 exam often tests the misconception that fine-tuning (Option B) is the best way to ground a model in proprietary data, but the trap is that fine-tuning does not provide dynamic, query-specific retrieval and can still produce hallucinations, whereas RAG explicitly forces the model to use retrieved facts.
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
✓
Implement Retrieval-Augmented Generation (RAG) with Azure AI Search.
Retrieval-Augmented Generation (RAG) with Azure AI Search grounds the model's responses in your company's internal knowledge base by retrieving relevant documents in real time and injecting them into the prompt. This reduces hallucinations by ensuring the model generates answers based on retrieved facts rather than relying solely on its parametric memory. Azure AI Search provides vector and hybrid search capabilities that efficiently index and query your documents, making RAG the most effective approach for factual accuracy.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Implement Retrieval-Augmented Generation (RAG) with Azure AI Search.
Why this is correct
RAG grounds responses in retrieved documents from Azure AI Search, so the model cites your internal knowledge base rather than relying on parametric memory. This directly minimises hallucination risk, satisfying the requirement for factual answers drawn from company content.
- ✗
Fine-tune the model on your company's documents.
Why it's wrong here
Fine-tuning adjusts the model's weights toward a style or format; it does not supply retrievable grounding, so the model can still fabricate facts absent from training. It suits teaching tone or output structure. Retrieval-augmented generation injects the knowledge base into the prompt, anchoring answers to source documents.
- ✗
Use few-shot prompting with examples of correct answers.
Why it's wrong here
Few-shot examples demonstrate answer format and style but add no factual grounding, so the model can still invent content beyond them. It suits steering output structure. Retrieval-augmented generation supplies the actual knowledge-base text at query time, which is what prevents fabrication.
- ✗
Set the max_tokens parameter to a low value.
Why it's wrong here
max_tokens caps response length only; a truncated answer can still be confidently wrong, so hallucination risk is unchanged. It suits controlling cost or latency. Grounding the prompt with retrieved knowledge-base passages is what constrains the model to factual source content.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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-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.