Project · 2026-11-02 · 2 min read

GDPad

A desktop data security solution that uses local AI and rules to detect and mask sensitive information before requests reach external AI providers

The challenge

AI requests can include customer contact details, confidential business information, or content from internal documents. The point before that information leaves the device is an opportunity to reduce the risk of unintentionally sharing sensitive data.

What we’re building

GDPad is a desktop data security solution being developed by Perfectory. It operates at the system level, intercepting requests before they reach external AI providers. Local AI models and rules detect and mask sensitive information on the user’s desktop.

Local-first architecture

We chose a local-first approach, placing detection and masking on the device where the work happens. Our goal is to fit that protection naturally into everyday workflows, with privacy and data security considered from the product’s foundation.

Prerelease and next steps

We’re preparing a prerelease version and inviting people and teams working with AI to share their use cases. What information needs protection, where do concerns arise, and what would make a desktop security tool useful in daily work?

Visit gdpad.io to request prerelease access or book a call with our team.

Get in touch