AWS Certified AI Practitioner (AIF-C01) — Question 134

A company is using a large language model (LLM) on Amazon Bedrock to build a chatbot. The chatbot processes customer support requests. To resolve a request, the customer and the chatbot must interact a few times.

Which solution gives the LLM the ability to use content from previous customer messages?

Answer options

• A. Turn on model invocation logging to collect messages.
• B. Add messages to the model prompt.
• C. Use Amazon Personalize to save conversation history.
• D. Use Provisioned Throughput for the LLM.

Correct answer: B

Explanation

The correct answer is B because adding messages to the model prompt enables the LLM to access prior conversations, allowing it to provide contextually relevant responses. Option A only collects logs without affecting the model's ability to refer back to previous messages. Option C, while related to conversation history, does not directly integrate past messages for real-time interaction. Option D is unrelated to message handling and focuses on throughput management.