Building a better Bugbot

How we used a custom AI-driven metric to systematically improve Bugbot.

Scaling long-running autonomous coding

We've been experimenting with running coding agents autonomously for weeks at a time.

Dynamic context discovery

As models improve as agents, we've found success by providing fewer details up front, making it easier for the agent to pull relevant context on its own.

The productivity impact of coding agents

A new study from the University of Chicago finds that companies merge 39% more PRs after Cursor's agent became the default.

Improving agent with semantic search

Semantic search significantly improves coding agent performance with 12.5% higher accuracy, improves code retention and decreases dissatisfied user requests.

Composer: Building a fast frontier model with RL

Composer is our new agent model designed for software engineering intelligence and speed.

Improving Cursor Tab with online RL

Our new Tab model makes 21% fewer suggestions while having 28% higher accept rate.

1.5x faster MoE training with custom MXFP8 kernels

Achieving a 3.5x MoE layer speedup with a complete rebuild for Blackwell GPUs.

Iterating with shadow workspaces

Hidden windows and kernel-level folder proxies to let AIs iterate on code without affecting the user.

More problems

Several exciting problem areas for the next phase of AI-programming.