Cursor's agent swarm suggests cheaper models can handle most coding when frontier models plan the work

Cursor's agent swarm suggests cheaper models can handle most coding when frontier models plan the work Jonathan Kemper View the LinkedIn Profile of Jonathan Kemper Jul 26, 2026 Nano Banana Pro prompted by THE DECODER Cursor pitted an upgraded agent swarm against its predecessor by asking both to rebuild SQLite in Rust using only the documentation, with no source code or internet access. Every configuration of the new system reached 100 percent on the test suite, while the old swarm bogged down in its own merge conflicts. At Cursor, agent fleets have moved from research project to core product. With Cursor 3, developers can run entire fleets of AI agents in parallel. Anysphere, the company behind Cursor, was recently acquired by Elon Musk's SpaceX for $60 billion. The system divides agents into two roles: planner agents using powerful frontier models recursively break a goal into smaller tasks. Worker agents using faster, cheaper models carry out those tasks. The result is a task tree that adapts as the work progresses. Cursor says this role split primarily solves a context problem. A lone agent has to traverse the entire tree while keeping both the goal and the current task in mind. That helps explain why agents drift during long jobs. In Cursor's swarm, planners don't write code, and workers don't plan. Cursor says swarms scale less through parallel work than by splitting context between planners that decide and workers that execute. | Image by Cursor Git could not handle 1,000 commits per second An earlier Cursor browser swarm reached about 1,000 commits per hour on Git. It used worker agents, a judge agent, and an integrator that resolved conflicts. The integrator ended up creating more bottlenecks than it removed. The new swarm reached 1,000 commits per second, so Cursor built its own version control system because agents working at that rate created failure modes that human teams never encounter. In what Cursor called "split-brain design," two planners would unknowingly build the same idea in different places and implement it in different ways. Contention was even harder to manage when planners knew about one another and blocked each other with competing edits. Cursor had agents record decisions in shared design documents. Code tied to a decision linked back to the document through a reference checked at compile time. When merge conflicts occurred, a neutral agent stepped in and resolved them. Workers flagged bloated files for an outside agent to split into smaller modules. Because agents had learned not to touch core code while working in existing codebases with humans in the loop, Cursor let them break things on purpose. An agent could patch code outside its assigned area, and the compiler would carry the change through the system. Multiple review angles and a self-maintained field guide Cursor tested several review approaches. One reviewer received the worker's full transcript, another saw only the output, and a third saw only the codebase. No single perspective caught everything, but uncorrelated perspectives combined for higher reliability. Cursor also tested a "field guide," a knowledge folder maintained by the agents themselves with a fixed line limit. Every agent received its contents at startup. Since model weights are frozen, it pays to capture surprising findings so later agents can take shortcuts. Cursor gave the swarm the 835-page SQLite manual and told it to build a Rust implementation. Source code, test suites, the SQLite binary, and internet access were all withheld. The benchmark was sqllogictest, a test suite with millions of SQL queries and known answers. The swarm didn't know it existed. Four configurations were tested. GPT-5.5 solo, Grok 4.5 solo, Opus 4.8 as planner with Composer 2.5 as worker, and Fable 5 as plann