A Demonstration of the RADAR Personal Assistant

Andrew Faulring, Carnegie Mellon University
Brad Myers, Carnegie Mellon University
Ken Mohnkern, Carnegie Mellon University
Michael Freed, SRI International

can be found at

http://repository.cmu.edu/hcii/262

Abstract or Table of Contents

Email clients were not designed to serve as a task management tools, but a high volume of task-relevant information in email leads many people to use email clients for this purpose. Such usage aggravates a user’s experience of email overload and reduces productivity. Prior research systems have sought to address this problem by experimentally adding task management capabilities to email client software. RADAR (Reflective Agents with Distributed Adaptive Reasoning) takes a different approach in which a software agent acts like a trusted human assistant. Many RADAR components employ machine learning to improve their performance. Human participant studies showed a clear impact of learning on user performance metrics.