2 Building a conversational AI
This chapter covers
- Building a Frequently Asked Questions (FAQ) conversational AI
- Building a process-oriented conversational AI
- Using generative AI inside of your conversational AI
To effectively improve a conversational AI, we need to know how such a solution is built. Let’s start by building our own conversational AI solution. This gives us a solid foundation for understanding their structure in general. It also sets the stage for understanding how we can improve each of the different kinds of solutions.
In this chapter, we follow a fictitious small American bakery in Ohio called Cake Shop. The company makes custom cakes and takes orders for delivery or pickup. They want to add a conversational AI solution to their website to help their customers. Since they have never built a bot before, they intend to start small but hope to quickly expand the scope and capability of their solution. They decide to start with an AI solution that can answer their most frequently asked questions.
We will demonstrate the building process using a conversational AI platform (IBM’s watsonx Assistant) and will later fold in a generative AI platform (IBM’s watsonx.ai). The key concepts we demonstrate are applicable across most conversational AI platforms (we discuss a few others you can try in Chapter 1).