Software factories and code reviews with Harjot Gill
CodeRabbit CEO Harjot Gill shipped over 5,000 pull requests in a month while spending $250,000 on AI.
5 comments
it's a good question! if you trust them as a vendor to iterate and improve their review system to tailor well to your eng best practices (or are nowhere near as advanced in it), it's a great way to start for a good while
but I do think the control and ability to really iterate on it, grow the review context/knowledge and scale it across the orgs is even mofe valuable
take the work I do with Entire as a replacememt for GitHub -> they have agent reviewers that run for their Trails (like PRs but agentic/faster w/ same governance + captures session context), but I find that injecting my own curated trail reviews alongside those does an even better job at reaching a confident implement in fewer steps, and I get to own that e2e! that savings and flex is where all the value is cuz I can ship durable changes 30-50% faster for the same token burn on avg
the sheer scale of agentic work done over there is mad-science curious... is anyone else operating at this scale, looking to business output for justify over $k/mo/engineer enterprise budgets?
type of thing I'd put to work on my verification layers when I get the budget & rationale...
I think we peaked at ~$10k/engineer (across 3 engineers at TLDR) when almost all usage was on Fable 5, but Opus 5.5 has cut that bill dramatically, now our total monthly spend token spend is between $10k-$20k for the whole team (including $100/month Claude seats for everyone).
I really loved CodeRabbit's reviews. But then their infrastructure started to lag a bit. I moved away from that and now use a set of skills/internal plugins to do review. I'm not sure if there's lift in the 3rd party version. (honest question)