Why would you create a monolith AI solution if you don't want to build a monolithic application for your enterprise?

Smaller models specific to each area of your company that are independently trained and managed allow you to experiment and quickly deploy complex AI solutions to your end users.

Model orchestration is a powerful tool that allows you to coordinate models across your organization to respond to users and complete tasks on your behalf.

In this session, I will walk you through training a custom model using distillation. I will also show you how to create a knowledge base using RAG. You will learn how, based on inputs and outputs, to create an orchestration over several models, knowledge bases, and even custom code.

I will use Amazon Bedrock and infrastructure as code to show you how to make the process repeatable and consistent in your environments.