Daily curated AI insights you can't miss.
Devin went from 16% to 80% of commits across Cognition repos after the December 2025 model inflection, and merged PR volume grew 7x.
The failure mode of pure auto-merge vibe coding is that after about two weeks, your codebase regresses to whatever the worst engineer produces.
Memory and retrieval are still unsolved—Devin auto-generates memories, but pruning stale knowledge and maintaining context across thousands of issues is still a manual burden.
The engineering world is waking up to a hard tension: hand-held coding, where a developer drives every keystroke, does not scale inside an organization that ships thousands of changes per week.
Walden Yan, Cognition‘s co-founder and CPO, frames this as the moment background agents go from toy to critical infrastructure.
The concrete proof is that Devin now generates 80% of commits across Cognition‘s own repos, up from 16% before the December 2025 model inflection, and merged PR volume has grown 7x.
The problem is not whether agents can write code—it is whether they can reliably go from a spec written in Slack to a merged, tested, properly reviewed pull request without breaking your codebase every two weeks.
Cole Murray‘s open-source OpenInspect project is an attempt to replicate this pattern for teams that cannot or should not buy a proprietary system.
