3 Designing effective processes

 

This chapter covers

  • Organizing user needs by complexity and frequency for a milestone plan
  • Identifying requirements for a minimum viable product
  • Assembling your dream team to implement a conversational AI
  • Addressing challenging parts of a process flow
  • Assembling appropriate responses for web and voice channels

A conversational AI is more than a classifier and some orchestration logic, in the same way that a graphical user interface is more than lines and styling. A conversational AI is a complete user experience channel; it requires a careful and thoughtful design for end users. The quality of your design sets an upper limit on how successful your conversational AI assistant can be.

This chapter focuses entirely on conversational AI design, setting aside almost all machine learning and coding considerations. After reading this chapter, you will be able to design process flows for your conversational AI, optimized for your preferred deployment channel, and you will be able to decide what processes you should implement first. You’ll be ready to learn how to write the dialogue supporting your new processes. Figure 3.1 shows the parts of your assistant that the user sees, but the invisible parts need to work well for a good user experience.

3.1 What processes will the assistant handle?

3.1.1 Designing for the most common user needs

3.1.2 Assembling a plan and a dream team

3.1.3 Managing the design process

3.1.4 Cross-cutting design aspects

3.2 Choosing the channel to implement first

3.2.1 How users receive information in voice and web

3.2.2 How the assistant receives information in voice and web

Summary

sitemap