Building Conversational AI to Augment Sales Teams at Structurely

Summary The true power of artificial intelligence is its ability to work collaboratively with humans. Nate Joens co-founded Structurely to create a conversational AI platform that augments human sales teams to help guide potential customers through the initial steps of the funnel. In this episode he discusses the technical and social considerations that need to be combined for a seamless conversational experience and how he and his team are tackling the problem. Announcements Hello and welcome to Podcast.__init__, the podcast about Python’s role in data and science. When you’re ready to launch your next app or want to try a project you hear about on the show, you’ll need somewhere to deploy it, so take a look at our friends over at Linode. With the launch of their managed Kubernetes platform it’s easy to get started with the next generation of deployment and scaling, powered by the battle tested Linode platform, including simple pricing, node balancers, 40Gbit networking, dedicated CPU and GPU instances, and worldwide data centers. Go to pythonpodcast.com/linode and get a $100 credit to try out a Kubernetes cluster of your own. And don’t forget to thank them for their continued support of this show! Your host as usual is Tobias Macey and today I’m interviewing Nate Joens about his work at Structurely to build conversational AI utilities that augment human sales interactions Interview Introductions How did you get introduced to Python? Can you describe what Structurely is and the story behind it? What are the elements that comprise a "conversational AI"? How is it distinct from the wave of chatbots that were popular in recent years? What lessons from that approach can we take forward into AI enabled conversational platforms? How are you applying AI to the sales process? How much domain expertise is necessary to make an effective and engaging conversational AI? (e.g. knowledge of sales techniques vs. knowledge of real estate, etc.) Can you describe how you have designed the Structurely platform? What are the biggest engineering challenges that you have had to work through? What challenges or complexities have been most persistent? What are the design complexities that you have to work through to make the AI accessible for end users? What are some of the advancements in AI/NLP/transfer learning that have been most beneficial for teams building conversational AI? What are the signals that you emphasize when monitoring the performance of your models? What is your approach for feeding real-world customer interactions back into your model development and training loop? What are the most active areas of research in conversational AI applications and techniques? What are the most interesting, innovative, or unexpected ways that you have seen Structurely and/or conversational AI used? What are the most interesting, unexpected, or challenging lessons that you have learned while working on conversational AI at Structurely? When is conversational AI the wrong choice? What do you have planned for the future of Structurely? Keep In Touch @whonatejoens on Twitter LinkedIn Picks Tobias Vantage AWS Cost Management Nate VideoForm Closing Announcements Thank you for listening! Don’t forget to check out our other show, the Data Engineering Podcast for the latest on modern data management. Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes. If you’ve learned something or tried out a project from the show then tell us about it! Email [email protected]) with your story. To help other people find the show please leave a review on iTunes and tell your friends and co-workers Links Stucturely GIS Generative AI GPT-3 Sanky Diagram PyTorch Podcast Episode Allen Institute for AI F Score Snorkel Podcast Episode Few-Shot Learning Zero Shot Learning Voxable The intro and outro music is from Requiem for a Fish The Freak Fandango Orchestra / CC BY-SA