Building NellyBot - How are we using Generative AI to build a Community support agent
We are going to explore Amazon Bedrock and how this solution can help you reduce the operational overhead of managing customer support. We are also going to learn about the fundamentals of prompt engineering and how can be used to orchestrate conversational flows.
Jose Yapur
Amazon Employee
Published Aug 13, 2024
Last Modified Sep 3, 2024
Authors: Ana Cunha (ana.dev) & Jose Yapur (develozombie)
We know you might think this is just another piece of content about Generative AI (GenAI). As developers, we get it—mainstream trends and buzzwords aren't always our thing. But we promise that this content series, which kicks off today, is different. It’s based on our personal experience implementing GenAI, where we'll share both the aspects we like and those we don’t.
This is the first article in a series where we’ll walk you through the creation of NellyBot, a virtual support agent designed to simplify tasks like AWS Credits requests and Q&A. A quick disclaimer: we are not AI/ML specialists. We’re developers, and this is our own adventure exploring these services for the first time.
We decided to kick things off with a video that summarizes everything. We're looking forward to hearing your comments and thoughts on what we're doing, as well as your opinions on GenAI for developers in general.
Next episode: How to use generative AI to become a better developer
Any opinions in this post are those of the individual author and may not reflect the opinions of AWS.