CodeRabbit CEO: AI agents reshape code review
Start here
CodeRabbit founder and CEO Harjot Gill says human review of individual pull requests is giving way to review of plans and releases. In an interview with The Pragmatic Engineer, Gill described a team of 40 engineers that shipped more than 5,000 pull requests last month while spending roughly $250,000 a month on AI, about $150 per PR. Gill said the company's agents check their own work using formal methods such as TLA+ and Lean, plus simulations, API emulation and staged rollouts. He also argued that fine-tuning models is no longer worthwhile because frontier models improve too quickly, and said CodeRabbit built its own agent-driven CI system in a week after being quoted $13 million a year for one.
Generated from reports · updated 1 d ago
Report timeline
Follow the reports to see the event from different sides.
- The Pragmatic EngineerSoftware factories and code reviews with Harjot Gill
Gergely Orosz interviews CodeRabbit founder and CEO Harjot Gill, whose team of 40 engineers shipped over 5,000 pull requests last month while spending roughly $250,000 a month on AI, about $150 per PR. Gill argues human code review of individual PRs is being replaced by review of plans and releases, and describes agents that verify their own work through formal methods like TLA+ and Lean, simulations, API emulation and staged rollouts. He also says fine-tuning models is no longer worthwhile as frontier models move faster, and that CodeRabbit built its own agent-driven CI system in a week after being quoted $13M a year for one.
Heat for this event
- Current, comparable range
- 5
- Peak, comparable range
- 10November 19 03:00
- Change in 24 hours
- -50%
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.