In the rationalistic perspective, the human expert is seen as a data-processing system having properties similar to computers. As a consequence, the design of man-machine interfaces, workplaces, and organizational procedures has been mainly driven by technological advances, focusing on replacing humans rather than supporting their actual needs. A more appropriate explanation of human cognition is based on the notion of situatedness: human cognition is considered to be emergent from the interaction of the human with the environment, i.e., the current situation the human is involved in. More generally spoken, the systemenvironment coupling is a prerequisite of cognition and cannot be abstracted away. In this paper, we summarize the rationalistic perspective, its pitfalls, and its (undesirable) influences on design. As an alternative, we propose "Situated Design", a design methodology capitalizing on the notion of the human as a situated agent. We demonstrate how "Situated Design" can be ...

The idea behind pervasive computing is that embedded and invisible technology calms our lives by removing the annoyances. Everyday life, however, is shaped by what people do, how they do it, and how they perceive what they are doing. As a consequence everyday life is difficult to grasp in computational terms. A look at the pervasive computing literature indicates that in a number of pervasive computing scenarios these difficulties are addressed by assuming that it is feasible to build intelligent behavior and common-sense understanding into pervasive computing environments. We believe that such assumptions are prominent among the reasons why many pervasive computing scenarios still sound like science fiction although most of the technologies required are readily available. Making these assumptions along with known difficulties explicit would greatly help pervasive computing become part of everyday life. Example scenarios from the pervasive computing literature will be used to illustrate a number of difficulties and some of the lessons to be learned from related disciplines having investigated similar ideas before.

This paper concerns a multi-agent system architecture for knowledge management (KM) systems in research and development (R&D) projects. R&D teams have no time to organize project information and to articulate the rationale behind the actions that generate the information. Our aim is to provide an architecture, which supports collaborative work and helps to capture and to organize experiences without overloading the team members with extra-work.

This paper concerns a multi-agent system for knowledge management (KM) for research and development (R&D) projects. R&D teams have no time to organize project information nor to articulate the rationale behind the actions that generate the information. Our aim is to provide a system for helping the team members to make knowledge explicit and to allow them to share their experiences, i.e., lessons learned (LL), without asking them too much extra-work. The article focuses on how we intend to help the team members to feed the system with LL, using the operations they perform on desktop computers, and how we intend to exploit the LL by using a case-based reasoning engine. We have been developing a prototype of such a KM system for a cooperative project. Early results will be presented.

this paper, we discuss implications of situatedness in its social and cultural meaning in the context of information seeking support. We proceed as follows. First, we discuss some of the varying meanings of the term \situated". Then, we outline how we interpret \accounting for situatedness" in the context of information seeking support. Finally, we discuss tools that implement aspects of what we consider important in this context.

This paper concerns a multi-agent system for knowledge management (KM) in research and development (R&D) projects. R&D teams have no time to organize project information and to articulate the rationale behind the actions that generate the information. Our aim is to provide a system that supports collaborative work and helps to capture and to organize experiences without overloading the team members with extra-work. Thus the gained experience can be continuously reused in the ongoing project as well as in the following ones. R&D teams perform project related tasks that can be modeled (e.g. as a workflow), but the corresponding sub-tasks are often unstructured (i.e., no predefined order, unpredictable resources) and hence are difficult to model. Such unstructured tasks are generally executed on the desktop, like writing a document, participating in technical discussions, or searching for documents. The article focuses on how we intend to automatically capture the unstructured tasks by using personal assistant agents, and how we intend to organize them as experiences (i.e., cases in the case-based reasoning sense). We have been developing a prototype of such a KM system for a cooperative project. Early results will be presented.

The Semantic Web is a vision to simplify and improve knowledge reuse on the Web. It is all set to alter the way humans benefit from the web from active interaction to somewhat passive utilization through the proliferation of software agents and in particular personal assistants that can better function and thrive on the Semantic Web than the conventional web. Agents can parse, understand and reason about information available on Semantic Web pages in an attempt to use it to meet users' needs. Such personal assistants will be driven by rules , axioms and the internal model or profile that the agents have inside them for the user. An intrinsic and important pre-requisite for a personal assistant or rather any agent is to manipulate information available on the Semantic Web in the form of ontologies, axioms, and rules written in various semantic markup languages. In this paper, a model architecture for such a personal assistant, which we call Sidekick, that deals with real-world semantic markup is described. The agent reasons with semantic markup written in DAML OIL, using the Java Expert System Shell (JESS) as the reasoning engine. This software assistant views information providers on the Semantic Web as recommender agents that have a limited view of the user's preferences and provides a improved notion of personalization by collaborating with peer personal assistants (what are referred to as buddy agents) within communities that the user has identified as trusted parties to exchange information with. Collaboration is achieved through simple This research was supported in part by DARPA contract F30602-97-1-0215.