The agent view provides a level of abstraction at which we envisage computational systems that are able to interoperate globally on “the Net”. It abstracts from aspects like the hardware or software platforms of various components or the internal structure, methods or processing of these components, focusing attention on how complex, heterogenous, distributed and evolving systems can be built from interoperable and reusable building blocks. From the practical point of view, multiagent systems engineering requires the ability to reuse abstract descriptions of system components, services, knowledge bases and coordination structures. Based on this recognition, we are developing an Agent Building Shell that provides several reusable layers of languages and services for building agent systems: coordination and communication languages, description logic based knowledge management, cooperative information distribution, organization modeling and conflict management. We are applying the approach to develop multiagent applications in the area of manufacturing enterprise supply chain integration.