Cursor scales hundreds of concurrent autonomous coding agents to run for weeks on large software projects
Single coding agents handle focused tasks well but are too slow for complex projects that typically take human teams months to complete; running multiple agents in parallel creates hard coordination problems including lock contention, risk-averse behavior, and duplicated work.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Ambitious goal assigned
An ambitious software goal is assigned to point the multi-agent system at a large project.
A planner/worker/judge hierarchy enabled hundreds of concurrent agents to run for weeks, producing over a million lines of code on ambitious projects including a from-scratch browser, a video rendering improvement of 25x that was merged to production, and a Solid-to-React migration passing CI.
What failed first
File-based locking for self-coordination created bottlenecks and brittleness; optimistic concurrency control was more robust but agents without hierarchy avoided hard tasks and made no real progress; an integrator role added for quality control created more bottlenecks than it solved.