of employees who use generative AI paste data into their prompts.
On-device privacy for AI prompts
Redact what AI shouldn't see.
PrAIvacy catches the names, emails, secrets and more in your ChatGPT prompts, then redacts them in one click before you hit send. Same on 10 more AI sites.
On-device · no accounts · never sent to a server
Your message
Draft a follow-up to Jane CohenNAME at jane.cohen@acme.comEMAIL about the Q3 renewal. Her direct line is (415) 555-0142PHONE.
3 findings redacted
Send ↵
Built for
ChatGPT
Also works on
Claude
Gemini
Copilot
Perplexity
DeepSeek
Grok
Meta AI
HuggingChat
Qwen
Kimi
Why it matters
Sensitive data goes into AI prompts every day.
of those pastes contain personal or payment data.
of pastes go through personal accounts that no company tool can see.
Source: LayerX, Enterprise AI and SaaS Data Security Report 2025, as reported by The Register.
How it works
Three steps, all on your machine.
A privacy model runs inside your browser and reads your draft as you type. The scanning never touches a network.
Detect
An on-device AI model reads your draft the moment you type it. No cloud call, no round-trip.
Flag
Sensitive spans get underlined and ranked by severity, from a stray name to a leaked secret key.
Redact
One click swaps each finding for a safe placeholder before you send. Copy the AI's reply and your originals come back.
On-device by design
Your prompts are scanned on your device.
Most "privacy" tools send your text to a server to scan it. PrAIvacy scans it right on your device instead.
Runs on your device
The detector is an open AI model that runs on your device. It downloads during setup, then works offline.
Your text isn't sent to a server
The scan runs on your device. PrAIvacy never uploads your text, to us or anyone.
No account, no telemetry
No sign-up, no tracking of what you write. Two Chrome permissions and access to the 11 AI chats it protects. That's it.
Privacy law
Built for privacy law, not around it.
GDPR, HIPAA, CCPA and most company AI policies share a basic rule: don't hand personal data or secrets to a service that doesn't need them. PrAIvacy helps you follow it in AI chats, and follows it itself.
For you at work
Names, emails, phone numbers, addresses, account numbers and API keys are flagged before you send, and one click swaps them for placeholders. The AI still gets your question, without the personal data.
PrAIvacy itself
We collect no personal data from the extension, so there is nothing for us to sell, share, or leak. Data minimisation and privacy by design (GDPR Article 25) are how it is built, not a feature added later.
Nothing to vet
No account, no server, no data processing agreement to sign. Your privacy team can read exactly what it does in the privacy policy.
GDPR & UK GDPR
ePrivacy
CCPA / CPRA
Israel PPL
COPPA
EU AI Act
Chrome Web Store Limited Use
PrAIvacy is a tool, not legal advice or a certification. It reduces what you share, but detection is best-effort and can miss things; you remain responsible for what you send.
FAQ
Questions, answered.
Is PrAIvacy free?
Yes. PrAIvacy is free and runs entirely on your machine. No account, no subscription.
What data does it collect?
None. Detection runs on your device, and PrAIvacy has no server that receives your text. No accounts, no analytics, no tracking. See the privacy policy.
Does it need an internet connection?
Only to download the detection model: once when you set up PrAIvacy, and again in the background when an update ships a newer model. Every check runs on your device, offline.
Can I add my own words?
Yes, and it's free. Select any term in the prompt box — a client name, a project codename, an internal system — and flag it. From then on it's underlined everywhere, whatever the model thinks. Your list stays on your device.
Which AI sites does it work on?
It's built for ChatGPT, and works the same way on Claude, Gemini, Copilot, Perplexity, DeepSeek, Grok, Meta AI, HuggingChat, Qwen and Kimi. It only touches those sites, never every website.
Which browsers are supported?
Chrome and other Chromium browsers like Microsoft Edge.
Can I get my original text back?
Yes. When the AI's reply mentions a placeholder like [EMAIL_1] and you copy that reply, PrAIvacy puts your original values back into what you copy. The website only ever sees the placeholders. The mapping lives in your browser's memory and is deleted when you close the tab.
Does PrAIvacy make us GDPR or HIPAA compliant?
No tool can do that on its own. PrAIvacy helps with the part that happens in the chat box: it flags personal data and secrets before you send them to an AI service and replaces them in one click. Compliance also depends on your contracts, your policies and what you choose to send. Detection is best-effort, so keep using your judgment.
Is PrAIvacy itself GDPR compliant?
It is designed so there is almost nothing to comply about: the extension collects no personal data, sends nothing you type anywhere, and stores its settings only in your browser. The only personal data we hold is email you send us, and you can ask us to delete it. The privacy policy explains how GDPR, CCPA, Israel's Privacy Protection Law and the other rules apply.
Can our IT or security team recommend it?
Yes. Nothing anyone types leaves their device, there is no account or server to vet, and PrAIvacy only has access to the 11 AI sites it protects. Admins can install it for managed Chrome browsers from the Chrome Web Store through Chrome's enterprise policies. For team questions, email hello@praivacy.info.
Stop pasting secrets into AI.
PrAIvacy is free and runs entirely on your machine.
Free · coming soon to the Chrome Web Store