I build fast, solve problems, and lead engineers.
Right now I'm building Merge Lantern, risk intelligence that tells small teams which pull requests need senior eyes before they merge.
I'm an Engineering Manager and Technical Architect. I turn ambitious roadmaps into shipped reality, broken and bloated systems into modern marvels, and chaotic sprints into calm, dependable releases — all without losing the human part along the way.
13 years in and I still love this stuff...the hard problems, the good teams, the moment it all clicks. Poke around; the rest of the site fills in the details.
When an agent helped write a pull request, the first question most reviewers ask is who wrote it. I think the better first question is what it touches. Here's how I'd set review depth by risk, where authorship still fits, and why some changes may need very little review at all.
When your team stops trusting its AI code review, the obvious fix is to add a second AI. I don't think that buys you much...two models trained on the same internet share the same blind spots. What actually helped me was checking the evidence outside the diff. I tried it on a real queue of 58 open PRs, and here's what it caught.
On a lot of teams, code that a pair of devs wrote usually gets a lighter code review. Nobody wrote that rule down and nobody voted on it, but pairing earned it. Here's what the research actually says about that discount, why it's never one flat size, and what happens when dev + agent starts getting filed under the same category.