Loubeth: An interactive Intelligent Agent for Electronic Negotiation*

Information systems with an intelligent or knowledge component are now prevalent and include knowledge-based systems, intelligent agents, and knowledge management systems. These systems are in principle capable of explaining their reasoning or justifying their behavior. This paper attempts to rectify this situation by drawing together the considerable body of work on the nature and use of explanations. Empirical studies, mainly with knowledge-based systems, are reviewed and linked to a sound theoretical base. In this paper we analyze: a) the process of negotiation between a user and an intelligent agent in a web store. The main purpose is to determine how the agent can utilize the user’s information to select the best price for him, b) The formulation of the negotiation allows us to determine how the agent works using a protocol for the user's satisfaction, and c) The use of KQML language for an application to interact with an intelligent agent named Loubeth, who will communicate with the user on his behalf for the acquisition of CD music according to his preferences. The agent presented can find an optimal path to achieve its goal using its mental states and libraries designed for the business roles. * This project has been funded by CONACYT as project number 33038-A, and Asociación Mexicana de Cultura, A. C.