Free IDE extension for risk-free vibe coding — keep secrets out of AI.
Monitor
POST /api/feedbackHelp SoterAI's detection models learn and improve by providing feedback on guard decisions. Mark false positives and false negatives to tune detection accuracy for your specific use case.
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 Detection Feedback.
Browse guard logs and mark any decision as correct, false positive, or false negative with one click.
Use POST /api/feedback 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 Detection Feedback, then review Guard Logs before enabling the control for production traffic.
No security system is perfect out of the box. Detection Feedback lets you train SoterAI's models on your specific data and use case, reducing false positives that frustrate users and catching true positives that might otherwise be missed.
A step-by-step breakdown of how Detection Feedback protects your AI.
Browse guard logs and mark any decision as correct, false positive, or false negative with one click.
Feedback is securely submitted to SoterAI's model training pipeline, anonymized and encrypted.
Your feedback is used to fine-tune detection models, improving accuracy across all risk categories.
Monitor your detection accuracy over time as the models learn from your feedback.
Quickly mark decisions as correct or incorrect from the logs view
Select and submit feedback on multiple log entries at once
Track your false positive/negative rates over time
Feedback is anonymized — content is never stored with your identity
This service is implemented at the application route below. Use the tested SDK and framework guides for copy-paste integration examples.
POST /api/feedback. API keys must stay server-side. See the REST API guide and related documentation before integrating.