Abstract: A web agent system automatically performs tasks for a computer user based upon the actions of the user. The web agent system includes a local assistant program stored on a user computer which performs various functions based upon rules and data. The local assistant program and rules are downloaded from a first local assistant server maintained by an application service provider. The data used with the rules by the local assistant program is downloaded from a second local assistant server maintained by an assisted merchant. The web agent monitors the user's actions and performs tasks related to the detected actions based upon the rules and data. The web agent also automatically updates the rules and data.

Abstract: A methodology and automated system are provided whereby a merchant presents timely and relevant information to customers. The system includes a client-side local assistant system and a server-side component. The client-side local assistant system, which is download installed on a customer's computer, implements an automated client-side system that is fully data driven. The data is partly downloaded data, called rulesets, and partly data that is collected and stored locally, called interaction data. The client-side system includes functionality for specifying and interpreting rulesets for observing, analyzing and storing information about, and relating to, computer-mediated customer interactions, such as viewing web pages or playing music. The client-side system also includes functionality for defining periodic tasks, such as gathering, analyzing and displaying information on topics of interest, and for direct interaction between the client-side system and the customer.