Optimizing Prompts For Large Language Models Using Amazon Bedrock

Large Language Models (LLMs) are powerful tools capable of summarization, classification, and question-answering. They also have mathematical and logical reasoning capabilities. To use an LLM most effectively, you need to craft and design a concise and accurate prompt.

Learning how to develop and design prompts for LLMs is a valuable skill that will benefit anyone looking to work with generative AI models.

In this hands-on lab, you will compare and contrast poor prompts with better ones, and you will examine techniques to improve the responses you receive.

Learning objectives

Upon completion of this beginner-level lab, you will be able to:

• Summarize and classify information using an LLM
• Control the randomness of the model's responses
• Specify the format of the response you want
• Improve the quality of the responses you receive

Intended audience

• Anyone looking to use Large Language Models in their workflow or applications
• Cloud Architects
• Data Engineers
• DevOps Engineers
• Machine Learning Engineers
• Software Engineers

Prerequisites

Familiarity with the following will be beneficial but is not required:

• Amazon Bedrock
• Large Language Models

The following content can be used to fulfill the prerequisites:

• Building and Scaling Generative AI Applications with Amazon Bedrock
• Introduction To Large Language Models

Updates

July 11th, 2025 - Updated lab instructions to use Amazon Nova Micro model