AWS Certified AI Practitioner (AIF-C01) — Question 285

A company wants to create a chatbot to answer employee questions about company policies. Company policies are updated frequently. The chatbot must reflect the changes in near real time. The company wants to choose a large language model (LLM).

Which solution meets these requirements?

Answer options

• A. Fine-tune an LLM on the company policy text by using Amazon SageMaker.
• B. Select a foundation model (FM) from Amazon Bedrock to build an application.
• C. Create a Retrieval Augmented Generation (RAG) workflow by using Amazon Bedrock Knowledge Bases.
• D. Use Amazon Q Business to build a custom Q App.

Correct answer: C

Explanation

Retrieval Augmented Generation (RAG) using Amazon Bedrock Knowledge Bases allows the chatbot to query external data sources in real-time, making it perfect for frequently updated policies without requiring constant model retraining. Fine-tuning a model via Amazon SageMaker is too slow and costly for near-real-time updates, and a standard foundation model lacks access to internal company documents. While Amazon Q Business is a powerful tool, setting up a RAG workflow with Amazon Bedrock Knowledge Bases is the standard, direct solution for integrating dynamic, external knowledge sources with an LLM.