Towards More Intelligent and Interactive Interfaces

Our goal is to support the development of more intelligent and more interactive text-based inter-faces for general computer use. In order to enable automation of user tasks, we find a new command shell architecture is needed. Our working proto-type, Fish, maintains a global, persistent knowl-edge repository across concurrent interactive ses-sions. For example, a user can define a shell func-tion in one session and this function is immedi-ately available to the user’s other concurrently running sessions, as well as future sessions. Our approach is to centralize knowledge in a persistent way while parallelizing execution. Fish is exten-sible and customizable, with a fuU programming language. It supports efficient communication be-tween the machine and the user in many ways, most notably by giving the user access to the re-suits of previously executed commands. Indexical references into previous results are possible by us-ing a sophisticated command language which con-tains a suite of syntactic and semantic analysis functions. Significant strides in learning are pos-sible due to the centralization of knowledge and its persistence. We illustrate the possibilities with an example of how learning may be uniquely applied using Fish