Privacy-First ArchitectureHow Guard Protects Your Data
A simple three-step process that keeps your sensitive information safe while you use AI.
SCAN
Guard analyzes your prompt in real-time, identifying all types of sensitive data including names, emails, phone numbers, credit cards, and more.
REDACT
Detected PII is automatically replaced with safe placeholders before your prompt reaches the AI model. Your original data never leaves your device.
RESTORE
When the AI responds, Guard seamlessly restores the original values in place of placeholders, giving you a natural conversation experience.
See It In Action
Hi, I'm John Smith and my email is john.smith@company.com. My credit card number is 4532-1234-5678-9012. Can you help me draft an email?
Hi, I'm [PERSON_1] and my email is [EMAIL_1]. My credit card number is [CREDIT_CARD_1]. Can you help me draft an email?
Detection Capabilities
Guard detects 50+ types of sensitive data across multiple categories.
Personal Information
- Full names
- Email addresses
- Phone numbers
- Social Security Numbers
- National IDs
- Passport numbers
Financial Data
- Credit card numbers
- Bank account numbers
- IBAN codes
- SWIFT codes
- Tax IDs
- Routing numbers
Medical Information
- Medical record numbers
- Health insurance IDs
- Patient identifiers
- Prescription info
Location Data
- Street addresses
- GPS coordinates
- IP addresses
- Zip/postal codes
Credentials & Secrets
- API keys (200+ providers)
- Passwords
- Access tokens
- SSH keys
- JWT tokens
Ready to Protect Your Data?
Get started with Guard in under a minute. Free forever for basic use.