Bugbot is now over 3x faster, 22% cheaper, and finds 10% more bugs

2026-06-10 · Source: Cursor Blog · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy · Depth: Intermediate, quick

Summary

Bugbot has received significant updates, making it over 3x faster to run, 22% cheaper, and capable of finding 10% more bugs per review. These enhancements mean 90% of Bugbot runs now complete in under three minutes. Users can now run Bugbot and Security Review with the "/review" command before pushing code, which also syncs with GitHub and GitLab to skip redundant reviews for the same diff. Additionally, Bugbot can be configured to review only new changes since the last push, focusing feedback on recent updates rather than re-reviewing the entire pull request. These performance improvements are attributed to harness enhancements and advancements in training Composer 2.5, which now powers Bugbot, with automatic fallback for organizations opting out of Composer 2.5.

Key takeaway

For MLOps Engineers or Software Engineers managing code quality, Bugbot's enhanced performance means you can integrate pre-push code reviews more efficiently. You should adopt the new "/review" command in Cursor 3.7+ to catch issues earlier and accelerate merge times, especially by configuring it to focus only on new changes. This approach will streamline your CI/CD pipeline and reduce review costs, ensuring faster feedback loops and higher code quality before pull requests.

Key insights

Bugbot's latest update significantly boosts speed, cost-efficiency, and bug detection through model and harness improvements.

Principles

• Pre-push reviews catch issues early.
• Focused reviews improve feedback relevance.
• Model upgrades drive performance gains.

Method

Use "/review" or "/review-bugbot" before pushing code to initiate a pre-commit scan, optionally configuring it to review only new changes.

In practice

• Run "/review" in Cursor 3.7+ before PRs.
• Configure Bugbot to review only new diffs.
• Utilize Composer 2.5 for optimal performance.

Topics

• Code Review
• Bug Detection
• AI Agents
• Composer 2.5
• CI/CD
• Software Quality

Best for: Software Engineer, AI Security Engineer, MLOps Engineer

Related on AIssential

• Before You Hit Push, Review Your Own Code — Proactive self-review, augmented by AI, elevates engineering quality and team collaboration.
• Cursor vs Copilot vs Claude Code: What Makes Developers 10x Faster? — Optimal AI-assisted development requires matching specific tools to specific tasks for compounded productivity gains.
• Meta Reports 4x Higher Bug Detection with Just-in-Time Testing — JiT testing dynamically generates targeted tests during code review, enhancing bug detection in AI-driven development.
• How Ramp engineers accelerate code review with Codex — AI tools like Codex can profoundly enhance developer productivity and code quality by automating complex tasks.
• Undo lands $37M to give AI agents the runtime context to fix bugs — AI agents require runtime execution history, not just code, to reliably diagnose and fix complex software bugs.
• Multi-Model Code Review: How Developers Can Catch Better Bugs Without Drowning in AI Noise — Structured multi-model code review, using narrow lenses and consensus aggregation, enhances human judgment by reducing AI noise.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Cursor Blog.