Matt Portillo chats with us about conversation design, why it isn’t really a project but is a long term journey.
Presented by Deepgram
Deepgram is a Speech Company whose goal is to have every voice heard and understood. We have revolutionized speech-to-text (STT) with an End-to-End Deep Learning platform. This AI architectural advantage means you don’t have to compromise on speed, accuracy, scalability, or cost to build the next big idea in voice. Our easy-to-use SDKs and APIs allow developers to quickly test and embed our STT solution into their voice products. For more information, visit:
Conversational AI projects: a marathon
Chatbots and voicebots are quick and easy. No problem at all. That’s the myth that needs to be shattered here. Many people, when they embark on their first conversational AI project, underestimate the amount of time and effort required to design, build, deploy and maintain their assistants
Matt Portillo, Conversation Design Lead at Amelia, joins us to share why conversational AI projects aren’t really projects; they’re long-term journeys as well as how you should prepare and the steps you should take to ensure success.
00:00 Intro and welcome Deepgram
02:50 Introduction of Matt Portillo
08:50 The avatar side of Amelia
15:30 Where a project begins and Matt’s involvement
24:22 How the conversation designer and NLU work together
28:15 Practice’s Matt would advise against/alternatives
33:19 The approach of validating the design decisions
37:40 The value of low fidelity prototyping
48:50 Why conversational AI in a long term journey
53:05 Principles people should be adhering to when it comes to conversation AI