AI0-001 Implementing AI Solutions Practice Question
A company is building a code generation assistant for internal developers. They want the assistant to generate code snippets consistent with the company's coding style and use private libraries. They have a few thousand examples of internal code. Which THREE considerations are critical when deciding between fine-tuning a base LLM and using RAG?
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
✓
RAG eliminates the need for any model updates when private libraries change, because it retrieves the latest documentation at inference time.
Fine-tuning can embed coding style and internal library knowledge into model weights, but requires regular updates. RAG is easier to update but may miss stylistic nuances. The volume of examples (a few thousand) is moderate; fine-tuning may still be feasible. Security and latency/availability are relevant for deployment.
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 a few thousand examples is insufficient; millions are required for any meaningful adaptation.
Why it's wrong here
With PEFT techniques like LoRA, a few thousand examples can be sufficient for domain adaptation.
- ✗
RAG requires the model to have a high context window size to accommodate retrieved code snippets.
Why it's wrong here
While helpful, many models already handle several thousand tokens; it's not a critical blocker.
- ✓
RAG eliminates the need for any model updates when private libraries change, because it retrieves the latest documentation at inference time.
Why this is correct
RAG retrieves from a vector store that can be updated without retraining the model.
- ✓
Security constraints may favour RAG because sensitive code is never part of the model's weights.
Why this is correct
RAG keeps source code in a controlled vector store; fine-tuning embeds it in model weights, which may be harder to audit.
- ✓
Fine-tuning can encode company-specific coding conventions directly into the model, reducing the need for style instructions in prompts.
Why this is correct
Fine-tuning adapts the model's behaviour, including style, which is harder to achieve with RAG alone.
About these practice questions
One of 754 original AI0-001 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 AI0-001 practice question is part of Courseiva's free CompTIA 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 AI0-001 exam.