The role of contextual information in intelligent assistant systems is cont
roversial. In this paper, we start from our experience of Intelligent Assis
tant System developers to clarify some notions about context and to study t
he question of context sharing. Moreover, we consider two important aspects
of man-machine cooperation, namely explanation generation and incremental
knowledge acquisition. Making context explicit in cooperative systems ir th
e key factor for any implementation of these two concepts. Starring from ou
r experience in the development of knowledge-based systems, especially of a
n interactive system far incident management in subway control, we explain
our views about context for the development of intelligent assistant system
s.