The paper describes experiences in applying a knowledge management too
l, called CODE, to the major knowledge management problems in the desi
gn of a large commercial software system, There is explanation of how
the design of such a product was documented as a CODE knowledge base b
y using CODE to carefully analyse all the important concepts and terms
in direct consultation with the developers, CODE could be described v
ariously as a 'design knowledge capture tool', a 'conceptual design as
sistant', or a 'knowledge management system for technical documentatio
n'. Its knowledge base and its highly interactive interface combine id
eas from frame-based knowledge representation systems, object-oriented
systems and hypertext systems, CODE is intended to augment and eventu
ally replace conventional word-processing and graphical tools for the
capture, editing and documentation of such knowledge. Hence it facilit
ates constructing definitions or descriptions of all the main concepts
in a system, validating these so that the system designers are in agr
eement, and retrieving and graphically displaying such knowledge in va
rious formats. CODE has been used in a wide variety of knowledge manag
ement situations, but here the focus is on its use in software enginee
ring design.