HeadsUpAI

Devin Now Coordinates a Team of Managed Devins in Parallel

· Updated

Devin, Cognition's AI coding agent, now coordinates a team of managed Devins. The main session scopes the work, delegates each piece to a managed Devin in its own isolated VM, monitors progress, resolves conflicts, and compiles results. Each managed Devin has its own terminal, browser, shell, and test runner, and reports back independently.

This matters because a single agent handling too much in one session accumulates context and loses focus. Parallel managed Devins each get a clean slate and a narrow scope. Devin also reads each managed Devin's full trajectory — what worked, what failed, where they got stuck — and uses that to improve how it scopes the next task.

Point Devin at a large refactor, QA sweep, or multi-service audit and ask it to spin up managed Devins for each piece. Each session has its own link so you can inspect its work or message it mid-task.

Cognition
Cognition
@cognition
X

Devin can now manage a team of Devins. Devin will break down large tasks and delegate them to parallel Devins that each run in their own VM. Over time, Devin gets better at breaking down and managing tasks for your codebase. Available now for all users. https://t.co/ig5PhoNASR

32retweets
View on X

Share this update