kitt
To encourage developers to build better chatbots, Seattle-based start-up, KITT.AI, has launched ChatFlow in private beta. Kitt.ai

To encourage developers to build better chatbots, Seattle-based start-up, KITT.AI, has launched ChatFlow in private beta. ChatFlow framework makes it easier for developers to build better chatbots that can hold multi-turn conversations and work on multiple platforms.

In 2015, Xuchen Yao was inspired to build KITT.AI when he realized there where “no good dialogue systems, and no good tools to create good dialogue systems,” he said.

KITT.AI originally focused on Amazon’s Alexa platform, then received Amazon’s Alexa Fund in 2015, and that’s when Yao set out to build his talented team.

How did the KITT.AI team meet? Yao met Guoguo when he went to JHU in 2010 to start a PhD. “We were in the same lab: Center for Language and Speech Processing (CLSP), headed by legendary pioneer to modern speech recognition Fred Jelinek. We’ve been planning to do a startup together.” Guoguo joined KITT.AI in 2016 after graduating from JHU.

“My mentor was Kenji Sagae, who just finished his PhD at Carnegie Mellon and a postdoc and took a faculty job at USC,” Yao told IBTimes. “We co-authored a few papers and have kept in touch since then. I convinced him to join KITT.AI around Thanksgiving 2015. That was when KITT.AI received Amazon’s Alexa Fund and I told Kenji: ‘now I have money to pay you, come over!’”

Microsoft and Facebook then fired up the bot hype in 2016 with Microsoft Bot Framework and Messenger Platform. All of a sudden chatbots started to become the new black.

To stand out from its competition, ChatFlow offers a Natural language comprehension engine for “one-shot” understanding, a multi-turn dialogue manager that controls conversational context, has great usability and features an intuitive drag-and-drop interface.

Yao believes developers have a hard time building a good chatbot because natural language understanding still isn’t solved and because they have been trained to build a graphic user interface, but not a language user interface.

KITT.AI has been building consumer facing chat apps for Facebook Messenger, Skype, telegram, Kik, Alexa, etc. In the near future, KITT.AI plans to support more enterprise chat apps in the future, but Yao said it's still too early to tell which ones.

More than 1000 people have already signed up to be on the waiting list. “Our ultimate goal is to have everyone who wants to program a chatbot using ChatFlow,” Yao said.

If you want to check out ChatFlow, you can sign up for the beta here.