In this hands-on workshop, you'll learn how to implement and manage AI configurations using LaunchDarkly's powerful feature management platform integrated with Amazon Bedrock's AI capabilities.
By the end of this workshop, you will:
- Set up a LaunchDarkly account and configure your Amazon Bedrock environment on AWS
- Implement the LaunchDarkly SDK and LaunchDarkly AI SDK in a Python application
- Create AI configurations in LaunchDarkly to enable dynamic control of which AI models and parameters are used without having to keep changing your application code
- Connect your application to AI foundation models (FMs) hosted in Amazon Bedrock such as Anthropic's Claude and Amazon Nova
- Implement tracking for user feedback and AI model metrics such as token usage, total cost and time to generate
- Create and manage AI experiments using LaunchDarkly to compare accuracy of models from different providers