Bugbot Effort Levels
TL;DR
Teams admins and Individual plan users can now customize Bugbot effort levels for PR reviews with Default, High, or Custom configurations based on natural language instructions. Usage-based billing is required for customization.
## What changed Cursor added effort level controls for Bugbot on May 18 2026. Teams admins and Individual plan users can now choose Default, High, or Custom modes for PR reviews. Custom mode accepts natural language instructions but requires usage-based billing to activate.
The update applies only to PR review workflows inside the Cursor platform. No changes were announced for other AI features such as inline chat or composer.
## Why it matters Granular effort settings let builders match review depth to project risk without rewriting prompts each time. This shifts Cursor from a fixed AI reviewer toward a configurable service that competes with lighter open-source alternatives.
The move bets that users will accept usage billing once they see measurable differences in bug detection rates. It pressures competitors who still offer only one-size-fits-all PR checks.
## How to use it Open the Cursor dashboard and navigate to the Bugbot section under workspace settings. Enable usage-based billing first, then select Custom and enter instructions such as focus on security or limit suggestions to performance issues. Changes take effect on the next PR review.
Individual users follow the same path inside their personal account settings. Test on a single repository before rolling out to a team.
## Watch for Track whether Custom instructions reduce false positives on large codebases. The bet breaks if token costs exceed the value of extra reviews. Expect Cursor to add effort presets for other tools such as test generation next.
Harsh’s take
Solo builders now face a clear trade-off. Default and High modes stay free or low-cost, but any real customization demands usage billing that can spike during active development sprints. The feature rewards teams that already live inside Cursor yet adds friction for anyone who prefers to keep AI spend predictable.
Most Vibe Builders will not need Custom instructions until they hit recurring review quality problems. Start by running a two-week test on one repository with usage billing capped at a low daily limit. If the extra reviews do not cut downstream bugs by at least 20 percent, switch back to Default and ignore the new controls.
by Harsh Desai
About Cursor
View the full Cursor page →All Cursor updatesMore from Cursor
- FeatureNew PR Review Experience and Parallel Building
Introduces a unified PR review interface with inline threads and commit history. New 'Build in Parallel' feature allows Cursor to execute independent plan tasks simultaneously using async subagents to speed up development.
- App UpdateCustomize Bugbot PR Review Effort
Admins and Individual plan users can now set Bugbot's effort level to Default, High, or Custom. High effort allows for deeper reasoning to find more bugs, while Custom effort uses natural language instructions to determine review intensity.
- IntegrationIntegrate Cursor with Microsoft Teams
Cursor is now available in Microsoft Teams. Users can mention @Cursor in any channel to delegate tasks to cloud agents, which can read thread context, select repositories, and create pull requests directly from the chat.