RADAR for productivity in the workplace

Many years after Apple's renowned Knowledge Navigator vision-video and Microsoft's ill-fated agent-as-eager-assistant Bob, Carnegie Mellon University's School of Computer Science (SCS) is creating a digital butler. Researchers at the School of Computer Science (SCS) have received an initial 7 million dollars from the Defense Advanced Research Projects Agency (DARPA) as part of a five-year plan to develop a software-based cognitive personal assistant that will help people perk up their productivity in the workplace. Nicknamed RADAR for Reflective Agents with Distributed Adaptive Reasoning, the software will aid its human master with tasks like creating coherent reports from snippets of information, scheduling meetings, and managing email by grouping related messages, flagging high priority requests and automatically proposing answers to routine messages. The idea is to develop a system that can both save time for its user and improve the quality of decisions, according to Carnegie Mellon University. RADAR will handle a number of routine tasks by itself and ask for confirmation on others. Over time, the system must learn when and how often to interrupt its busy user. Whether the system will be rendered as a photo-realistic human (providing laconic commentary) remains to be seen, but a number of techniques from a variety of fields will be employed, including machine learning, human-computer interaction, natural-language processing and flexible planning.