The 'MECIMPLAN' Approach to Agent-Based Strategic Planning

Despite the wide range of problems in which planning is used, it is possible to utilize a common methodology that allows us to reach specific planning objectives for a real problem. From a software engineering point of view, the methodology assures us the quality of the process and the product. In this paper we introduce a methodology that permits us to construct models in order to solve planning problems at any project environment through the use of agents. We have built a prototype for strategic planning that presents us with an alternative solution to the well-known `prospective' technique. It is particularly relevant for planning problems that are concerned with decisions that have a long-term impact. The results obtained through the construction of prototypes illustrate the adequacy of our approach. This paper is organized as follows: we first give a general overview of the methodology. In Section 2, we illustrate the approach by a case study in the domain of strategic planning. Section 3 presents an agent-based prototype that implements the case study. We conclude the paper by stating the lessons learnt from this enterprise