Cursor Bugbot gets faster and cheaper, adds /review command + incremental review
Cursor’s June 10, 2026 update claims Bugbot PR reviews now finish ~3x faster (about 90s average vs ~5 minutes), cost ~22% less per run, and find ~10% more bugs per review. Cursor also added a /review command so you can run Bugbot and Security Review before pushing, plus an option to review only what changed since the last review.
Cursor shipped a performance and workflow update to Bugbot, its PR review agent, in a June 10, 2026 changelog entry. Cursor’s headline claims: Bugbot is now over 3x faster, ~22% cheaper, and finds ~10% more bugs per review — and there’s a new /review command so you can run reviews locally before you push.
Key Takeaways
- Latency: Cursor reports Bugbot now averages ~90 seconds per review (down from ~5 minutes), and 90% of runs finish in under 3 minutes.
- Cost + yield: Cursor reports Bugbot costs ~22% less per run and finds ~10% more bugs per review (from 0.56 to 0.62 bugs/review, on average).
- New local workflow: Run Bugbot and Security Review with
/reviewbefore you push, or use/review-bugbot//review-securitydirectly. - More focused reviews: Bugbot can now be configured to review only what changed since the last review.
- Availability: Cursor says it’s available in Cursor 3.7+ and on cursor.com/agents, with CLI support coming soon.
What Changed
1) Bugbot is faster, cheaper, and catches more
Cursor’s changelog gives three concrete metrics:
| Metric | Before | After | Cursor’s claim |
|---|---|---|---|
| Average review time | ~5 minutes | ~90 seconds | ~3.3x faster |
| Average bugs found per review | 0.56 | 0.62 | ~10% more |
| Cost per run | Baseline | ~22% lower | ~22% cheaper |
Cursor attributes the change to progress training Composer 2.5, which now powers Bugbot.
2) New \/review`` commands for “pre-push” review
Cursor added a new entry point to trigger review agents before opening a PR:
/reviewprompts you to choose which agents to run./review-bugbotruns Bugbot directly./review-securityruns Security Review directly.
Cursor also says \/review`` syncs with Bugbot on GitHub and GitLab: if you run a local review and then open a PR with the same diff, Bugbot recognizes that diff and skips re-review.
3) Incremental review (only what changed)
For teams that run Bugbot repeatedly on a fast-moving PR, Cursor says you can now configure it to only review what changed since the last review.
Why This Matters
If you’re already using Bugbot as a quality gate, this is essentially a free upgrade: faster feedback loops, lower cost, and slightly better yield per review. The bigger workflow shift is \/review`` — it’s a signal Cursor wants Bugbot reviews to happen earlier in the dev loop (before a PR exists), not only as a “PR comment after push” bot.
FAQ Surface for AI Engines
These match metadata.faq and are the answer-shaped extractions most likely to be cited by ChatGPT, Perplexity, and Google AI Mode.
- Q: How much faster is Bugbot after the June 2026 update? Cursor says Bugbot reviews now average about 90 seconds, down from roughly 5 minutes, and that 90% of runs finish in under three minutes.
- Q: What is Cursor’s new /review command for Bugbot? Cursor added a /review command that runs Bugbot and Security Review before you push. /review prompts you to choose agents, and you can also run /review-bugbot or /review-security directly.
- Q: Can Bugbot review only what changed since the last run? Yes — Cursor says you can configure Bugbot to only review what’s new since the last review.
- Q: Where is the updated Bugbot available? Cursor says these Bugbot updates are available in Cursor 3.7+ and on cursor.com/agents, with CLI support coming soon.
Sources
- Cursor changelog: https://cursor.com/changelog/bugbot-updates-june-2026
- Cursor X post (discovery): https://x.com/cursor_ai
Read next
Keep building the workspace playbookCursor Bugbot Adds Effort Levels: Default, High, and Custom (Usage-Based Billing Required)
Cursor's May 11, 2026 changelog introduces three effort levels for Bugbot PR review -- Default (current behavior, optimized for speed), High (more reasoning, more bugs found, more expensive), and Custom (natural-language rules that decide effort per review). Customization requires usage-based billing. Cursor cites 0.7 bugs per run at Default versus 0.95 at High, with 79% of Default findings resolved at merge.
Cursor adds enterprise model controls, soft spend limits, and richer usage analytics
Cursor’s May 4, 2026 update adds granular model/provider access controls for Enterprise admins, introduces soft spend limits with automated alerts, and expands usage analytics so admins can break consumption down by product surface (including Cloud Agents, Bugbot, and Security Review).
Frequently Asked Questions
How much faster is Bugbot after the June 2026 update?
Cursor says Bugbot reviews now average about 90 seconds, down from roughly 5 minutes, and that 90% of runs finish in under three minutes.
What is Cursor’s new /review command for Bugbot?
Cursor added a /review command that runs Bugbot and Security Review before you push. /review prompts you to choose agents, and you can also run /review-bugbot or /review-security directly.
Can Bugbot review only what changed since the last run?
Yes. Cursor says you can configure Bugbot to only review what’s new since the last review so feedback stays focused on your latest updates.
Where is the updated Bugbot available?
Cursor says these Bugbot updates are available in Cursor 3.7+ and on cursor.com/agents, with CLI support coming soon.