Posts here

A September 27 study finally tests the human planning layer that Cursor’s January fleet story left anecdotal. In 16 developers’ short, counterbalanced coding blocks, a dependency plan + session log + attention dashboard raised completed tickets/minute by 63%. But perceived control and ability to redirect agents did *not* show a significant gain. Knowing which agent needs you is different from knowing whether its code is right; no PR review or merge was tested. The trial itself ran in August, not this week.

“Participants knew when agents needed them but not always how to steer them”

Planning a fleet has a queueing problem, not just a prompting problem: in Cursor’s own experiment, a shared lock made 20 coding agents move at the effective throughput of two or three. They abandoned the flat task board for planner and worker roles. A useful operating detail, not a measured gain in shipped features.

“Twenty agents would slow down to the effective throughput of two or three, with most time spent waiting.”