Designing conversational applications is intrinsically hard. There are a number of different disciplines that are required, from machine learning all the way to brand management and conversational content management.
A conversational application platform needs to embrace this complexity and ensure that different disciplines can come together effectively to produce great solutions.
In order, however, for us to be able to deal with the complexity, without getting lost along the way, we need to start from a strong conceptual core and build out. For conversational applications this conceptual core has to be a model of conversations themselves.
We need a strong understanding of what are conversations, what are the component parts and how do they interact to build increasingly more complicated solutions and handle sophisticated multi-turn conversations.
So let's start with how we think of conversations.
If you are after a longer intro on what we think some of the challenges of conversational application are please check out the talk below on "Conversational applications that work smarter, not harder".