Free IDE extension for risk-free vibe coding — keep secrets out of AI.
Control
POST /api/dry-run/simulateSafe sandbox environment to simulate and evaluate agent actions before they're executed in production. Test policies, validate changes, and train models without risk.
Complete these steps in order. The dashboard link opens the exact product workspace for this service.
Sign in, select the project you want to protect, then open Dry Run Sandbox.
Send sample agent actions to the dry-run endpoint with realistic content and context.
Use POST /api/dry-run/simulate from server-side code. Keep API keys out of browsers and client bundles.
Run one safe case and one expected-risk case. Confirm the result in Dry Run Sandbox, then review Guard Logs before enabling the control for production traffic.
Testing security policies in production is dangerous. Dry-Run Sandbox lets you simulate agent actions against your policies in a safe environment, so you can see what would be blocked, allowed, or flagged — without any real-world impact.
A step-by-step breakdown of how Dry-Run Sandbox protects your AI.
Send sample agent actions to the dry-run endpoint with realistic content and context.
Actions are evaluated against your active policies exactly as they would be in production.
See the simulated decision (ALLOW/BLOCK/REDACT/APPROVE), risk score, and detailed reasoning.
Adjust policies based on dry-run results, then re-run simulations to validate changes before deploying.
Evaluate actions against policies with zero production impact
Full decision context including risk scores, matched rules, and reasoning
Run multiple simulations at once for comprehensive policy testing
Compare how different policy versions would handle the same actions
This service is implemented at the application route below. Use the tested SDK and framework guides for copy-paste integration examples.
POST /api/dry-run/simulate. API keys must stay server-side. See the REST API guide and related documentation before integrating.