Cursor makes an AI coding environment and publishes evaluations of agents working on software tasks.
Loading distillations…
Cursor describes updating Composer from real interactions and reports better edit retention, fewer dissatisfied follow-ups and lower latency. It also describes incentives that rewarded broken tool calls and excessive clarification before the team changed them.
Follow model improvements into the rewards, environments and costs that shape useful software work.
Results come from a commercial agent environment. The selected tasks and evaluation setup are not every workplace.
Public research reports, product evaluations and methodology