Skip to content

Leena AI builds discussion robots to automatically answer political questions

Suppose you have a job in a large company and want to know how much time you have left, or how to add your new baby to your health care. This usually involves sending e-mails or calling HR and waiting for an answer, or even going through multiple systems to get what you need.

Leena AI, a member of the Y Combinator Summer 2018 class, wants to change that by building RH robots to instantly answer employees' questions.

The robots can be integrated into Slack or Workplace by Facebook and they are built and trained using information contained in policy documents and pulling data from various back-end systems like Oracle and SAP.

Adit Jain, co-founder of AI Leena, says the company has its roots in another startup called Chatteron, which the founders started after they left the university in India in 2015. This product helped people to build their own chatbots. Jain said along the way, they discovered while doing their market research, a particularly strong need in HR. They started Leena AI last year to meet this specific requirement.

Jain said during the construction of bots, the team learned from his experience with Chatteron, that it is better to focus on a single subject because the model of machine learning under -jacent improves as much as it is used. "Once you've created a robot, so it's really useful and accurate, and it's really deep, it takes a lot of time and effort, and it can not be done only by verticalization, "explains Jain.

Photo: Leena AI

In addition, as the founders are more familiar with the needs of human resources, they learned that 80% of the questions address similar topics such as vacations, sick leave and expense reports. They have also seen companies using similar back-end systems, so they can now create standard integrators for common applications such as SAP, Oracle and Netsuite.

Of course, even though people may ask similar questions, the company may have unique terminology or people may ask the question in an unusual way. Jain says that's where the natural language processing (NLP) comes in. The system can learn these variations over time by building a larger database of possible queries.

The company has just launched in 2017 and already has a dozen paying customers. They hope to double that number in just 60 days. Jain believes that being part of Y Combinator should help in this regard. The partners help the team refine their presentation and make presentations to companies who could use this tool.

Their ultimate goal is nothing more than to be ubiquitous, to help bridge the gap between several existing systems to provide employees with answers seamlessly to all their Questions. If they can do it, they should be a successful business.

See also  A million dollar Bitcoin ransom would have been paid for the kidnapped EXMO executive