AI tools for coding: Cursor, Copilot, Claude Code, v0, Bolt
We apply online reinforcement learning to Composer, serving model checkpoints to production and using real user interactions as reward signals to ship an improved checkpoint multiple times a day.
Self-hosted cloud agents keep your code and tool execution entirely in your network.
How we're building indexes for regular expression search so agents can find text in large monorepos without the 15-second ripgrep waits.
Frontier-level coding with strong CursorBench results, higher token efficiency, and a faster default variant.
By making self-summarization part of Composer's training, we can get training signal from trajectories much longer than the model's max context window.
Cursor's security team built a fleet of security agents to find and fix vulnerabilities across a fast-changing codebase.
We use a hybrid online-offline eval process to keep our understanding of model quality aligned with what developers actually do.
Extend Cursor with prebuilt capabilities in our marketplace.
Cursor now supports automations that run based on triggers and instructions you define.
Use Cursor agents in IntelliJ IDEA, PyCharm, WebStorm, and other JetBrains IDEs through the Agent Client Protocol.
By collapsing code, logs, team knowledge, and past conversations into a single Cursor session, we've removed the context-gathering bottleneck for most of our support work.
Bugbot saves PlanetScale the equivalent of two full-time engineers worth of review effort.