Razor is a planning-based information-gathering softbot that assists users by automatically determining which Internet information sites are relevant to their query, accessing those sites in parallel, and integrating the results. Razor uses a disjunctive graph-based plan representation. It then uses a novel and powerful form of local completeness reasoning in order to transform those plans into contingent plans of high quality. These contingent plans can be efficiently executed, obtaining more answers at less cost than the original plans.

For more information:

• Mark Friedman, Daniel S. Weld Efficient Execution of Information-Gathering Plans (IJCAI-97, August 1997)