Q5 — AWS AIF-C01 Ch.3

Question 5 of 100 | ← Chapter 3

A company wants to build an internal chatbot application using Amazon Bedrock to answer employee questions based on internal documentation. The company aims to minimize application development costs. Which solution will minimize operational overhead to meet these requirements?

• A. Use fine-tuning to adapt an LLM with the company's data
• B. Use continual pre-training to adapt an LLM with the company's data
• C. Create a knowledge base and use retrieval-augmented generation (RAG) ✓
• D. Train an LLM from scratch using only the company's data

Correct Answer: C. Create a knowledge base and use retrieval-augmented generation (RAG)

Explanation

RAG leverages existing internal documents via efficient retrieval without requiring expensive model training, retraining, or infrastructure setup. It delivers accurate, context-aware responses while significantly reducing development effort, compute cost, and maintenance overhead compared to fine-tuning, continual pre-training, or training from scratch.