Four layers of guardrails with locked rules and exemptions. Global security policies that cannot be overridden. Group-level inheritance for teams. Project-level customization. Per-job fine-tuning.
naming/branch: ai/*
Branch names must start with ai/
LOCKEDmax_file_changes: 10
Overridable at lower scopes
content-pattern: no-console
Block console.log in all repos
LOCKEDmax_file_changes: 15
← overrides global (10)
no-public-rds: critical
New rule added at group scope
naming/branch
✕ cannot override — LOCKED
max_file_changes: 20
← overrides group (15)
testing/min-coverage: 80%
Specific to this project
Effective rules this project
max_files:20 · no-console · ai/* branch
Set maximum files an expert agent can change per job. Prevent sprawling, unreviewed modifications.
Cap the number of lines changed. Keep changes focused and reviewable.
Block expert agents from specific directories entirely. Protect infrastructure, config, and sensitive paths.
Restrict expert agents to specific directories only. Ensure changes stay within scope.
Detect and reject forbidden code patterns using regex. Catch security anti-patterns automatically.
Enforce branch, commit, and merge request naming standards. Consistency without manual review.
Mark critical global rules as locked. No group or project can exempt them. Security policies that cannot be overridden.
Groups and projects can exempt non-locked parent rules. Full audit trail of what was exempted and why.
The Play Workbench lets you validate guardrail rules against real changes — before they go live.
Request Early Access