Privacy Policy

This policy explains what AI Diff Guard collects and how it is handled. We are committed to data minimisation and to compliance with India’s DPDP Act and the GDPR.

What we process

Code diffs: when you run an analysis (web or via the GitHub App), the diff is sent to our analysis engine in-memory to generate the review. We do not retain your source code. We store only result metadata — risk score, finding categories, file paths, PR number — to power your dashboard.

Account & billing: for paid plans we store your email and the payment reference returned by Razorpay/Stripe. We never see or store full card details.

Anonymous usage: a first-party cookie holds an anonymous visitor id to enforce free-tier limits. We use privacy-friendly, cookieless analytics for aggregate traffic.

LLM processing

Analysis runs on a self-hosted model gateway on our own infrastructure. Diffs are not used to train any model and are not shared with third-party AI providers for training.

Your rights

You may request access to or deletion of your stored data at any time by emailing getdeaddictedllc@gmail.com.

Data retention & security

Result metadata is retained while your account is active. Databases are backed up daily. Access is restricted and traffic is served over HTTPS.