Cognition launches Code Scans to turn engineering goals into pull requests via Devin
Cognition has released Code Scans, a Devin AI feature that lets engineers state a broad goal—like improving SEO or reducing maintenance overhead—and have the system investigate the codebase, evaluate findings, and generate pull requests automatically. It uses an 'Agentic MapReduce' architecture, the same one behind Devin Security Swarm, splitting large investigations into parallel batches and merging results into a single report before creating PRs. Early testers, including Philips' informatics team, report a 96% PR merge rate and over 700 engineering hours saved during trials.
GoKawiil's interpretation of the reporting above, not reported fact.
Many engineering priorities stall because the investigative groundwork—finding where to make changes—is more time-consuming than the fixes themselves. By automating both discovery and implementation, Code Scans could shift AI coding assistants from reactive helpers to proactive drivers of large-scale codebase improvements, potentially reshaping how technical debt and compliance work gets prioritized.
- Code Scans lets users start from high-level goals rather than specific code changes.
- It uses parallel AI agents (Agentic MapReduce) to investigate and synthesize codebase findings into reports and PRs.
- Early adopters like Philips reported a 96% PR merge rate and 700+ engineering hours saved.
Source: devin.ai, 2026-09-18
Published there as: “Code Scans”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.