Read more about how we set up our cloud agent environment:

Cursor describes simplifying its development environment so cloud agents could run and test the software they changed. Written skills documenting its convoluted build commands helped only on the margins, according to its engineering account. The team therefore built anydev, a command-line tool for starting services and running common utility scripts, with a supervisor that monitors and restarts long-running build commands. This removed process management from the model's responsibilities. With a working environment and computer use, agents could test changes end to end and share recorded demos on pull requests or in Slack. The concrete change was making verification easier to execute within the development environment. Engineering account.

“Getting our monorepo working for cloud agents taught us that the development environment is a product in its own right, only one whose users are agents. You have to make cloud match local development, make the repo legible enough that agents can run and test code without tribal knowledge, and keep that environment healthy as the codebase changes.”

cursor_ai

“In December, cloud agents authored roughly one in ten PRs merged to the Cursor monorepo. Today, they write more than half.”

cursor_ai

“We wrote skills for how to build and run many parts of the system, but this only helped on the margins. Skills can document the right commands, but those commands themselves were convoluted and filled with footguns.”

cursor_ai

“To reduce that complexity, we built a CLI called anydev, which agents can use to start all services. We route common utility scripts through anydev as well, and equipped anydev with multiple --help menus explaining how to use each subcommand. anydev also has a supervisor process which monitors and restarts long-running build commands, removing that responsibility from the model entirely.”

cursor_ai

“This is when cloud agents, each with their own computer, began to add real value over local agents. With computer use, their recordScreen tool, and a working dev environment, agents could now test their changes end-to-end, and prove the correctness of their work to the user.”

cursor_ai