Wrote Coval's account of building and measuring its automated code reviewer.
Why their word counts: Builds and runs the reviewer described in the post and reports its measurements; an insider.
Profile from this source , checked 2026-11-07 .
“ Asked to name sensitive risk domains in prose, the model claimed authorization in 38% of reviews, while about 18% of the changes touched anything authorization-shaped; required to quote the specific changed line instead, it produced 570 claims, of which 98% resolved to real code—the same model over the same pull requests, with only the form of the question changed.” Dana Dzik Engineer, Coval (author of the Coval blog post on its code reviewer) · Practitioner ,
Post: Notes on Building a Code Reviewer , Coval blog , September 10, 2026, at The rebuild .
[ Grade B ] Said in the last year Sells AI tools Passage page
“ In August, people at Coval opened 2,578 pull requests and pushed roughly 3,400 further commits to them after they were first marked ready.” Dana Dzik Engineer, Coval (author of the Coval blog post on its code reviewer) · Practitioner ,
Post: Notes on Building a Code Reviewer , Coval blog , September 10, 2026, at Introduction .
[ Grade B ] Said in the last year Sells AI tools Passage page
“ Reviews are capped at three findings, a partly arbitrary number kept because it measurably changes whether people read the output; and silence is the usual outcome, 922 of the 1,732 recorded runs of this design having published nothing, a mean of 0.70 findings per review.” Dana Dzik Engineer, Coval (author of the Coval blog post on its code reviewer) · Practitioner ,
Post: Notes on Building a Code Reviewer , Coval blog , September 10, 2026, at The rebuild .
[ Grade B ] Said in the last year Sells AI tools Passage page
“ In its first week in production the roster brought the median cost per review from about thirty cents to eleven while publishing at roughly the same rate.” Dana Dzik Engineer, Coval (author of the Coval blog post on its code reviewer) · Practitioner ,
Post: Notes on Building a Code Reviewer , Coval blog , September 10, 2026, at The roster .
[ Grade B ] Said in the last year Sells AI tools Passage page
“ The configuration that catches the most of what our human reviewers catch is also the cheapest one we have run, and most of its budget goes to models that would be dismissed on sight as too weak for code review—which, individually, they are.” Dana Dzik Engineer, Coval (author of the Coval blog post on its code reviewer) · Practitioner ,
Post: Notes on Building a Code Reviewer , Coval blog , September 10, 2026, at Where it goes .
[ Grade B ] Said in the last year Sells AI tools Passage page
Coval