2 min lesson

Trust progression: approve-each-fix, then graduate to auto-fix

Think through this situation: "A team wants to turn on Bugbot's auto-fix for every repo on day one. What's the recommended rollout instead, and what dashboard would you point their director at?" Give the practical answer in plain words.

Trust progression: approve-each-fix, then graduate to auto-fixearn autonomy a rung at a time

BugbotCursor's automated PR reviewer that posts inline findings and can push fix commits from isolated VMs. Press Enter for the full definition.'s config lives in an admin dashboard with four knobs worth knowing cold: which repos it operates on, the scrutiny level, whether it runs per-PR automatically or on a manual trigger, and whether it is surface-only or allowed to auto-fix. The recommended rollout is a trust progression: start with auto-fix off so a human approves every proposed fix, watch the resolution rate and false-positive rate, and only graduate a repo to auto-fix once the team trusts the signal. It's the same propose-then-earn-autonomy pattern as the bright line (section 5), applied to a single tool.

Learn more

Full explanation

The leadership dashboard

BugbotCursor's automated PR reviewer that posts inline findings and can push fix commits from isolated VMs. Press Enter for the full definition. also exposes an engineering-leadership view: last-30-days PRs reviewed, issues resolved and automatic fixes merged, drillable down to a specific repo and broken out by severity (high / medium / low). This is the surface that turns AI review from a feature into an ROIReturn on Investment. The value gained versus what it cost, the language an economic buyer funds deals in. Press Enter for the full definition. story. When a director asks 'is this worth it?', you don't hand-wave. You point at 30 days of resolved high-severity issues per repo. It's also the honest counter to volume metrics: it counts issues resolved, not lines touched.

Bugbot at a glance

Trigger: Auto-runs on PR open and update, on every push to the PR
Output: Inline comments on the exact lines of concern
Customization: .cursor/BUGBOT.md holds repo- and area-specific custom rules
Autofix: Isolated cloud-VM agents propose bounded fixes that humans still review before merge
Speed (Jun 2026): ~90-second average review time; ~22% lower run cost; ~10% more bugs found (verify)
Resolution: Consistently resolves north of 70-80% of the issues it raises (verify)
Dashboard: Leadership view: last-30-days PRs reviewed / issues resolved / auto-fixes, by repo and severity

Trust progression: approve-each-fix, then graduate to auto-fix

Step 1 of 3