Case-based systems enable users to retrieve previously known designs from memory and adapt them to fit the current design problem. The four case-based design systems described here illustrate how various implementations achieve design assistance or design automation objectives.

Case-based reasoning is a problem-solving technique that makes analogies between a problem and previously encountered situations (cases) relevant to solving the problem. Using CBR as a design process model involves the subtasks of recalling previously known designs from memory and adapting these design cases or subcases to fit the current design context.

The detailed development of this process model for a particular design domain proceeds in parallel with the development of the case representation, the case memory organization, and the necessary design knowledge. The selection of an information representation paradigm and the details of its use for a problem-solving domain depend on the intended use of the information, the project information available, and the nature of the domain.

CBR could be used to develop and implement a CBR system. Although that sounds circular, if CBR is a viable approach to problem solving, it can be applied to the development of the reasoning system itself. Toward that end, this article presents four "cases" of case-based building design systems that we've developed at the University of Sydney: CaseCAD, CADsyn, Win, and Demex. These systems exemplify alternative case memory contents and organizations and provide insight into different potential implementations of the recall and adaptation subprocesses.