From Software Factory to Model Factory @TheWuster from Cognition uses @DevinAI to train a custom image model on @modal, deploy it, and ship it into a product

Devin Fusion. Better and cheaper.

How Autofix and Devin Review Ship Clean Pull Requests on Their Own

Dynamic workflows let Devin split a big job into pieces, hand each one to its own Devin, and bring the results back together. The plan for a Dynamic Workflow lives in code instead of an agent’s head, so you always know which Devins will run, in what order, and what each one is told.

The hardware you run no longer dictates where or what you can build macOS, Linux, Windows, and Android cloud environments on-demand with Devin

Devins can start managed Devins of their own, so one task can branch into a tree of Devins several levels deep. Work done in sequence takes as long as all its parts added together, while work split this way takes roughly as long as its slowest part. So size stops being the reason a task gets postponed, since a larger task simply produces a larger tree.

Security Swarm sends a swarm of parallel Devins through your codebase to build a threat model, hunt down real, exploitable vulnerabilities (even ones chained across files), prove them in a sandbox, and hand you the fix as a pull request. Here's how it works:

Cloud agents get much more useful when they can run the real toolchain: xcodebuild, the iOS Simulator, Computer Use tapping through the UI. Every Devin session gets its own cloud Mac so mobile work can be delegated like any other ticket. Here's how it works:

Fusion in Devin Desktop & CLI Fusion achieves frontier intelligence while being up to 39% cheaper. Use your favorite frontier model for planning and a cost-effective model for execution. Fable/Astra + SWE-2 is very cost-effective during SWE-2’s free promo.