How we set up our cloud agent environment
Cursor’s cloud-agent adoption grew after it treated the dev environment as agent infrastructure: Linux parity, one discoverable CLI, end-to-end testing, and automated repair.
Cursor moved its monorepo onto agent-ready Linux VMs, centralized startup and utilities in an internal CLI, and added end-to-end computer-use testing. Cloud agents went from **roughly 1 in 10 merged PRs in December** to **more than half today**.
Treat the development environment as part of the agent harness. Match cloud and local dependencies, replace fragile command sequences with one discoverable interface, expose verification workflows, and let supervisors own long-running processes.
Cursor moved its monorepo onto agent-ready Linux VMs, centralized startup and utilities in an internal CLI, and added end-to-end computer-use testing. Cloud agents went from **roughly 1 in 10 merged PRs in December** to **more than half today**. Treat the development environment as part of the agent harness. Match cloud and local dependencies, replace fragile command sequences with one discoverable interface, expose verification workflows, and let supervisors own long-running processes. Skills alone only helped at the margins because the underlying commands remained convoluted. Cursor also built **Cursor Cloud MCP** and **Cloud Doctor** to diagnose and repair environment failures, but the adoption figures are internal and do not isolate which change caused the increase.
This supplies implementation detail behind Cursor’s earlier claim that complete environments drive cloud-agent reliability and adoption: dependency parity, one discoverable CLI, supervised processes, end-to-end testing, and automated diagnosis mattered more than extra instructions alone. It therefore narrows skill-centric approaches: skills cannot compensate for a fragile execution surface, and the internal adoption increase does not identify any single causal change.