Speaker "Pamela Bhattacharya" Details Back


Topic - a virtual scheduling assistant


Scheduling meetings is tedious. It gets even more challenging when people use different calendaring systems or meet across different time zones. People need to have multiple dialogues to find an optimal time for them to meet that takes away their ability to focus on more demanding tasks. Surveys on hundreds of information workers, in a wide range of industries and roles, have citied scheduling meetings as the most cumbersome task. While online calendar sharing tools like Outlook and Google calendar and polling tools like Doodle make scheduling less cumbersome, users still do not have a seamless scheduling experience. Leveraging state-of-the-art artificial intelligence (AI), we created a virtual assistant that could handle the conversational back-and-forth required for scheduling meetings, much the same way that executive admins schedule meetings for CEOs. In this talk, I will present, a system that provides fast, efficient scheduling through structured workflows. Users interact with the system via email, delegating their scheduling needs to the system as if it were a human personal assistant. I will describe the iterative approach we used to develop, and share the lessons learned from scheduling thousands of meetings.


Pamela Bhattacharya is a Principal Applied Scientist at Microsoft. Currently she is the tech lead for scheduling intelligence that powers the virtual scheduling assistant in Cortana, also known as She is passionate about designing and engineering end to end user experiences powered by AI that can help users be more productive by helping them manage their time. She wears multiple hats in her current role - she has contributed as the developer/architect for the back-end workflows in the product, as well led the research and development in natural language understanding and designed ML techniques to personalize scheduling experience. Prior to joining Microsoft, she completed her PhD from University of California, Riverside.