Imagining the future of conversation with machines

Most (if not all) conversational interaction with artificial intelligence is based on the recognition of keywords and phrases. Developed over decades of research based on cognitive science and linguistics, Patom Theory was created to teach machines language and how it is structured. This approach allows machines to learn to learn, similar to how humans learn. I was fortunate to work with the team at Pat to help move product development forward through research, strategy, and design.

What is Patom Theory?

"Patom theory postulates that all a brain can do is store, match and use patterns. The assumption is that a pattern cannot be divided beyond a certain point, and as it is indivisible, I call it an atom. That’s why we have the name pattern atom, or patom." - John Ball

Research & Discovery

We started with an affinity diagram and customer journey. As the problems to solve became clear, we created messaging and supporting materials to aid Pat in progressing through the partner engagement and commercialization process.

Human-Machine Conversation Design

We developed demos for the technology through application to real-world scenarios based on customer needs and engagement. This conversation flow created in Axure is for a travel booking.