Wedescribe the use of a recommendersystem to enable continuousknowledgeacquisition and individualized tutoring of application software across an organization. Installing such systemswill result in the capture of evolving expertise and in organization-widelearning (OWL).Wepresent the results of a year-long naturalistic inquiry into application's usagepatterns, basedon loggingusers' actions. Weanalyzethe data to developuser models,individualized expert models,confidenceintervals, and instructional indicators. Weshowhowthis information could be used to tutor users.