AIF-C01 Fundamentals of Generative AI Practice Question
A company is building a chatbot that must provide accurate answers based on internal documents without retraining the model. Which approach should they use?
⚠ Common exam trap
Test-takers frequently confuse fine-tuning (which requires retraining) with RAG (which does not), or mistakenly think RLHF or distillation can inject new factual knowledge without retraining, when in fact they address alignment, efficiency, or behavior, not dynamic knowledge retrieval.
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) allows the chatbot to fetch relevant internal documents at inference time and incorporate them into the prompt, providing accurate, up-to-date answers without retraining the model. This approach combines prompt engineering with a retrieval step, ensuring the model's responses are grounded in the company's specific knowledge base while keeping the base model frozen.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Reinforcement learning from human feedback (RLHF)
Why it's wrong here
RLHF optimises model behaviour against human preference rankings; it cannot retrieve internal documents and needs reward-labelling effort. It is tempting because it aligns responses with human expectations, and it would be correct for tuning helpfulness or safety rather than supplying factual grounding from a knowledge base.
- ✗
Fine-tuning the model on internal documents
Why it's wrong here
Fine-tuning alters model weights and requires labelled training data plus retraining cycles, which the question explicitly excludes. It is tempting because it genuinely improves tone and task-specific behaviour, and it would be correct when a fixed style or format must be learned rather than current documents retrieved.
- ✗
Model distillation to a smaller model
Why it's wrong here
Distillation compresses an existing model into a smaller one, preserving learned behaviour but adding no connection to internal documents. It is tempting because it cuts inference cost and latency, and it would be correct when deployment footprint or throughput matters more than grounding answers in a document corpus.
- ✓
Prompt engineering with retrieval-augmented generation (RAG)
Why this is correct
Retrieval-augmented generation retrieves relevant passages from internal documents at query time and supplies them as context, so the chatbot answers from current source material without retraining. Prompt engineering shapes how that retrieved context is used, meeting the no-retraining constraint.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services 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 AIF-C01 exam.