We describe a briefing system that learns to predict the contents of reports generated by users who create periodic (weekly) reports as part of their normal activity. We ad- dress the question whether data derived from the implicit supervision provided by end-users is robust enough to sup- port not only model parameter tuning but also a form of feature discovery. The system was evaluated under realis- tic conditions, by collecting data in a project-based univer- sity course where student group leaders were tasked with preparing weekly reports for the benefit of the instructors, using the material from individual student reports.