Core Engine

AI that respects
your boundaries.

Three layers of guardrails ensure agents never modify files they shouldn't, exceed change limits, or violate your coding patterns.

Request Access

Three layers of safety

Layer 1

Global

Platform-wide rules that apply to every agent, every project, every task. Your organization's baseline security posture.

Max 50 files per task, block /infrastructure/
Layer 2

Project

Project-specific overrides that tighten or adjust global rules. Each project can define its own constraints.

Only allow /src/ directory, enforce naming conventions
Layer 3

Task

Per-task fine-tuning for maximum control. Override any rule for a specific task when needed.

Max 5 files for this bugfix, block test files

Layers merge with specificity priority: task overrides project, project overrides global.

What you can constrain

File Limits

Set maximum files an agent can change per task. Prevent sprawling, unreviewed modifications.

Line Limits

Cap the number of lines changed. Keep changes focused and reviewable.

Directory Restrictions

Block agents from specific directories entirely. Protect infrastructure, config, and sensitive paths.

Allowed Directories

Restrict agents to specific directories only. Ensure changes stay within scope.

Pattern Enforcement

Detect and reject forbidden code patterns using regex. Catch security anti-patterns automatically.

Naming Conventions

Enforce branch, commit, and merge request naming standards. Consistency without manual review.

Test your guardrails before deploying

The Play Workbench lets you validate guardrail rules against real changes — before they go live.

Request Early Access