we've been working with @nvidia for nearly a year now. i'm excited to share more about our work together! --- some background: nvidia was an early adopter of many coding agents. like many forward-thinking teams, validation became their new bottleneck. they understood deeply that they needed independent code validation. they chose to partner with @greptile for a few reasons: - greptile's ability to find bugs outside the diff (second order effects of changes) - greptile's ability to deeply understand their large, highly specialized codebase - greptile's ability to enforce custom coding standards the impact: - more bugs caught, especially logic bugs - up to 80% reduction in merge times - far less review load on senior engineers and managers learn more here:

"coding is the bottleneck." coinbase engineering leader @chintanturakhia disagrees. below is my full conversation with chintan, probably the most AI-native engineering leader in the world, on how he runs his engineering team.

introducing greptile's linear integration greptile: - finds the linear issue associated with your PR (even if it isn't linked) - ensures that the PR fulfills the requirements of the issue. sometimes PRs aren't buggy, just incomplete. some of the best teams define "complete" in linear!

launching 5 things: 1. multi-repo context support 2. rebuilt web app for super large orgs 3. integrations with claude/codex/devin 4. .greptile/rules files 5. rebuilt learning so greptile maintains internal docs about your company

you can now get devin to fix issues flagged by greptile with one click, launch a devin session that includes the issue and relevant context. greptile and devin will loop until greptile gives the PR a 5/5 this has become the default way in which i use greptile