Modeling typical enterprise information systems requires the modeling of multiple agents with different functionalities. This paper describes a methodology that provides the representational formalism, coordination mechanisms, and control schemes necessary for integrating heterogeneous units of distributed information systems while meeting such performance criteria as overall effectiveness, efficiency, responsiveness, and robustness. An important component of the methodology is the coordination among agents. The framework is applied to the development of a manufacturing information system for managing the production processes for making printed circuit boards. Performance results confirm that the multi-agent framework for system integration is important to support complex business processes that involve multiple steps of activities processed by a group of agents across a variety of functionalities. The framework also provides an unified model for integrating software and decision modules in complex information systems.