Exploring the Web with reconnaissance agents
Henry Lieberman, Christopher Henry Fry, Louis Weitzman · Communications of the ACM · 2001
This article reports on a new agent technology that helps Internet surfers to scout out the online terrain and recommend the best paths for the user to follow. These agents are called reconnaissance agents, programs that look ahead in the user's browsing activities and act as an advance scout to save the user needless searching and recommend the best paths to follow. Reconnaissance agents are also among the first representatives of a new class of computer applications, learning agents that infer user preferences and interests by tracking interactions between the user and the machine over the long term. Two examples of reconnaissance agents are provided in the article are that of Letizia and PowerScout. The main difference is that Letizia uses local reconnaissance, searching the neighborhood of the current page, while Powerscout uses global reconnaissance, making use of a traditional search engine to search the Web in general. Both the Letizia and the PowerScout style of agent have their advantages and disadvantages. This new technology permits users to maintain a focus on their quest for information while decreasing the time and frustration of finding material of interest.