CoreShieldCoreShield AI
User Guide

01

What CoreShield is & the four verbs

CoreShield is a Sovereign AI Privacy Gateway: use external AI models without your sensitive data ever leaving your environment.

In short

CoreShield detects the sensitive information in your documents, replaces it with tokens before anything reaches an external AI provider, then restores your originals in the reply — all inside your environment and under your control.

The four governing verbs

  1. Detect: sensitive entities are identified in your document.
  2. Cloak: originals are sealed in the vault and replaced with a semantic token.
  3. Send: only the cloaked content ever reaches the AI provider.
  4. Restore: the AI response is rehydrated with your originals, locally.

This is a pilot

This is a pilot running on synthetic data only. Do not enter any real personal data.

No raw value ever leaves your environment; the gateway enforces this by design.