This article argues that a DAI approach can be used to cope with the complexity of industrial applications. DAI techniques are beginning to have a broad impact; the current introduction of these techniques by an ESPRIT project, a Palo Alto consortium, ARPA, Carnegie Mellon University, MCC, and others are good examples. In the near future, other industrial products will emerge from the application of DAI techniques to other domains, including distributed databases, computer-supported cooperative work, and air traffic control. An important advantage of a DAI approach is the ability to integrate existing standalone knowledge-based systems. This factor is important because software for industrial applications is often developed in an ad hoc fashion. Thus, organizations possess a large number of standalone systems developed at different times by different people using different techniques. These systems all operate in the same physical environment, all have expertise that is related but distinct, and all could benefit from cooperation with other such standalone systems

This paper describes how a set of autonomous computational agents can cooperate in providing coherent management of transaction workflows in environments where there are many diverse information resources. The agents use models of themselves and of the resources that are local to them. Resource models may be the schemas of databases, frame systems of knowledge bases, domain models of business environments, or process models of business operations. Models enable the agents and information resources to use the appropriate semantics when they interoperate. This is accomplished by specifying the semantics in terms of a common ontology. We discuss the contents of the models, where they come from, and how the agents acquire them. We then describe a set of agents for telecommunication service provisioning and show how the agents use such models to cooperate. The agents implement virtual state machines, and interact by exchanging state information. Their interactions produce an implementation of relaxed transaction processing. 1

In this paper we describe how a set of autonomous computational agents can cooperate in providing coherent management of information in environments where there are many diverse information resources. The agents use models of themselves and of the resources that are local to them. Resource models may be the schemas of databases, frame systems of knowledge bases, or process models of business operations. Models enable the agents and resources to use the appropriate semantics when they interoperate. This is accomplished by specifying the semantics in terms of a common ontology. We discuss the contents of the models, where they come from, and how the agents acquire them. We then describe a set of agents for telecommunication service provisioning and show how the agents use such models to cooperate. Their interactions produce an implementation of relaxed transaction processing. 1