An agent oriented approach is well suited for complex application domains, and often when such applications are used by domain experts they identify modifications to be made to these applications. However, domain experts are usually limited in agent programming knowledge, and are not able to make these changes themselves. The aim of this work is to provide support so that domain experts are able to make modifications to agent systems. In this paper we report on an evaluation of our Component Agent Framework for domain Experts (CAFnE) framework and toolkit, giving a detailed account of a usability study we conducted with a group of experienced meteorologists.
The Component Agent Framework for domain-Experts (CAFnE) toolkit is an extension to the Prometheus Design Tool (PDT). It uses the detailed design produced by PDT with further annotations by domain experts to automatically generate executable code into a desired agent platform. The key feature of CAFnE is that it allows domain experts with limited programming skills to easily build and modify agent systems.
Service oriented architecture (SOA) is a widely used model for enterprise application integration, mainly due to the presence of accepted standards and tools required to implement web services. While the service oriented architecture provides an elegant model for interoperability, it does not define a computational model for building the endpoints of complex distributed services it exposes in a typical enterprise application. On the other hand, software agent technology provides powerful models such as the Belief-Desire-Intention (BDI) model that allows developers to build distributed systems with enhanced reasoning capabilities. We propose a web services based communication model for interagent communication allowing heterogeneous agents in a multi agent system to freely collaborate. We specifically focus on goal and beliefset sharing in BDI based agents. By providing a web services based interface, we allow agents as well as non-agent based services in a distributed system to yield the benefits of agent technology. Applicability of this proposition is demonstrated by designing and implementing a prototype multi-agent system for flood forecasting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.