This paper presents CoCo, a system that automates web tasks on a user's behalf through an interactive conversational interface. Given a short command such as "get road conditions for highway 88," CoCo synthesizes a plan to accomplish the task, executes it on the web, extracts an informative response, and returns the result to the user as a snippet of text. A novel aspect of our approach is that we leverage a repository of previously recorded web scripts and the user's personal web browsing history to determine how to complete each requested task. This paper describes the design and implementation of our system, along with the results of a brief user study that evaluates how likely users are to understand what CoCo does for them.
Digital paint is one of the more successful interactive applications of computing. Brushes that apply various effects to an image have been central to this success. Current painting techniques ignore the underlying image. By considering that image we can help the user paint more effectively. There are algorithms that assist in selecting regions to paint including flood fill, intelligent scissors and graph cut. Selected regions and the algorithms to create them introduce conceptual layers between the user and the painting task. We propose a series of "edge-respecting brushes" that spread paint or other effects according to the edges and texture of the image being modified. This restores the simple painting metaphor while providing assistance in working with the shapes already in the image. Our most successful fill brush algorithm uses competing least-cost-paths to identify what should be selected and what should not.