Bugbot was already the best code review agent in the world. Now it’s 3x faster and catches more bugs.
In a world where the volume of PRs per engineer is 10x what it used to be, high quality review becomes the biggest bottleneck to shipping. Check out Bugbot if you haven’t already:
https://t.co/O7z98bYUE1
It’s a game changer.
Cursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs.
You can also use /review to run Bugbot locally to catch and fix issues before pushing code.
@jonathan_wilke@cursor_ai Ah I see, sounds like you're referring to the native Linear integration in Cursor. For the time being we only support one workspace but this is good feedback. Hopefully MCPs can serve as a viable workaround soon!
One of the coolest use cases of the SDK is to build on @wilsonzlin’s work orchestrating massive agent swarms for complex tasks. /orchestrate makes it effortless to do so!
Introducing /orchestrate, a skill that recursively spawns agents to tackle your most ambitious tasks with the Cursor SDK.
We’ve used it to:
- Autoresearch our internal skills, cutting token use by 20% while improving evals
- Cut cold start times on our internal backend by 80%
Managing my coding agents from within my game itself via @cursor_ai's agent sdk - instant access to backend gamestate, front end visuals, and my existing suite of runtime performance analytics.
Some queries can now just be: "this looks wrong" - quite helpful for playtesting and debugging
Narrative violation: Finding it's more fun to work within Cursor than in the native Codex or Claude Code apps.
Not a massive difference, but just enough to keep me there. And obviously easier to play with new competing models as they come out.
Nice work, Cursor.
Excited to share what I’ve been working on recently! The SDK provides a super ergonomic interface for the Cursor agent and we’ve already seen early users building some mind blowing projects on top of it!
Everything from rebuilding the Cursor CLI from scratch, to massive orchestrated agent swarms, and bespoke desktop applications for running local agents!
Check it out and let me know what you think!!
We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor.
Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.