In recent years, we have experienced an explosion in the amount of information available online. Unfortunately, tools which allow users to access this information are still quite rudimentary. Users are forced to express their information needs in boolean query languages. More, results returned are often unnecessarily redundant and poor in quality. In response to the problems posed by the current state of information retrieval systems, we are working on a class of systems we call Personal Information Management Assistants (PIMAs), aimed at solving these problems. Essentially, PIMAs allow everyday applications to serve as interfaces for Internet information systems.

PIMAs observe user interaction with everyday applications (such as Microsoft Word, or Netscape) and apply information-consumption scripts to anticipate a user's needs. Then they attempt automatically fulfill them by employing appropriate Internet information sources (such as AltaVista), filtering the results, and presenting them to the user. We report on the two basic processes associated with accomplishing these tasks: query generation and information filtering. Our prototype PIMA uses a heuristic term-weighting function to compose a query based on the text and structure of the active document. Then, it sends this query to an appropriate Internet information source. On the return end, it processes the results using a heuristic result similarity metric, clustering similar pages, and presenting single representatives to the user.

In this paper, we report on our preliminary work on an architecture for this class of systems, and our progress implementing such a system. We exhibit two information-consumption scripts, and demonstrate several scenarios in which they apply. Finally, we present preliminary results and survey directions for future work.