Autonomous AI Agents Now Generating 35% of Cursor's Internal Pull Requests as Developer Workflows Shift Dramatically
Summary
Autonomous AI agents are reshaping software development at Cursor, now generating 35% of internal pull requests as agent usage surges over 15x in one year, with developers increasingly directing fleets of parallel AI agents rather than relying on traditional line-by-line autocomplete tools.
Key Points
- A third era of AI software development is emerging, defined by autonomous cloud agents that tackle large tasks independently over longer timescales, reducing the need for constant human direction.
- Agent usage in Cursor has surged over 15x in the past year, with agent users now outnumbering Tab users 2-to-1, as developers shift from line-by-line autocomplete to directing fleets of parallel AI agents.
- 35% of pull requests merged internally at Cursor are now created by autonomous cloud agents running on virtual machines, returning reviewable artifacts like logs, video recordings, and live previews instead of raw code diffs.