Feldr is a browser extension that intercepts every prompt to ChatGPT, Claude, Gemini, Copilot, and agentic AI tools - detecting and redacting PII, PHI, and secrets before they ever leave your browser.
Protecting prompts to
See it in action
The same detection you’ll see live in your own browser - a real AWS key, caught and masked in under 12ms, across every AI tool your team uses.
The problem
Every day, people paste customer records, credentials, and financial data into ChatGPT, Claude, Gemini, and Copilot to get work done faster. None of it is malicious - and almost none of it is noticed until the data is already gone.
SSNs, medical record numbers, and customer identifiers pasted into a prompt to draft an email or summarize a case.
AWS keys, Stripe secrets, and OAuth tokens dropped into an AI coding assistant to debug a failing request.
Card numbers and account balances shared with a chatbot while reconciling an invoice or a client statement.
Proprietary algorithms and internal system prompts copied into a public model to get a faster answer.
Wherever your team already works
How it works
It all happens right inside your browser, in a fraction of a second. You won't notice a thing - but your private information never leaves your side.
Feldr is a small browser add-on. When you type into ChatGPT, Claude, Gemini, Copilot - any AI tool - it quietly follows along in the background.
In a split second - right on your own computer - it recognises sensitive things like names, card numbers, passwords, and health details. Nothing is sent away to check.
The instant it finds something private, Feldr blanks it out or swaps it for ▓▓▓ - before your message ever reaches the AI. You keep working; the real data stays with you.
Every save is noted in a simple dashboard, so admins can see what was protected and set the rules - without ever seeing the private data themselves.
Security & architecture
Every payload is detected and neutralized in the browser, then masked at the boundary - only the redacted, policy-approved version ever crosses into a prompt, a request, or a log.
Sensitive payloads are scanned locally by the extension and never sent to Feldr's own cloud for scanning.
Every redaction is recorded as a policy-evaluated event for audit - the raw SSN, key, or card number is never stored.
One extension install covers ChatGPT, Claude, Gemini, Copilot (in Chrome and Firefox; Edge does not allow extensions there), and any agentic tool you open in the browser.
Detection catalog & coverage
48 detectors across four categories, deployed wherever your team types a prompt - and every match logged, live, in one console.
Chrome, Edge, and Firefox - intercepts every prompt typed into a web AI tool.
Wraps outbound calls from MCP agents and internal tools before they reach a model.
Compliance & trust
Feldr's architecture is designed to support the compliance frameworks your security team already audits against — data never leaves the browser to begin with.
Controls designed to meet SOC 2 Type II security and availability criteria.
Built to handle protected health information end to end.
Data minimization and in-browser processing by design.
Card data is redacted before it's ever transmitted.
Pricing
Per user per month, in US dollars. Team and Business start with a 14-day free trial.
Protect every AI chat your team uses.
$4.20per user / month
billed annually · Minimum 10 seats
Identity, compliance and control for growing organisations.
$8.40per user / month
billed annually · Minimum 25 seats
For large or regulated organisations.
Custom
From 500 seats, or in-country hosting
FAQ
How Feldr detects and redacts sensitive data before it reaches ChatGPT, Claude, Copilot, and every other AI tool your team uses.
Feldr is an AI privacy browser extension. It detects and redacts PII, PHI, secrets, and financial data before they ever reach ChatGPT, Claude, Gemini, Copilot, or any other AI tool.
Feldr reads your prompt in the browser as you type, recognizes sensitive data on-device in milliseconds, and masks or blocks it before the message is sent - so the raw data never leaves your browser and never reaches the model.
No. Detection runs entirely on-device in your browser. Plaintext is never sent to Feldr's cloud for scanning - only redaction events (never the raw data) are logged for audit and compliance.
ChatGPT, Claude, Gemini, Microsoft Copilot, Perplexity, and other web-based and agentic AI tools - all from a single browser-extension install, with no per-tool setup. One exception: Microsoft Edge does not let extensions run on Microsoft Copilot, so Feldr protects Copilot in Chrome and Firefox, and blocks it in Edge (your administrator can change this).
PII such as SSNs, emails, and phone numbers; PHI such as medical record numbers and insurance IDs; credentials and API keys such as AWS keys and OAuth tokens; and financial data such as card numbers and IBANs - across dozens of detectors.
Feldr is built for regulated data. Because detection happens on-device and raw sensitive data is never stored or transmitted, it is designed to support HIPAA, GDPR, PCI-DSS, and SOC 2 requirements.
Yes. Admins can force-install Feldr on every managed browser in one step using standard enterprise policy - Google Admin console, Windows Group Policy, or Microsoft Intune - with centralized policy control and a full audit trail.
Feldr runs detection on-device so plaintext never leaves the browser, covers every AI surface from one install, records audit events without ever storing the raw data, and starts with a 14-day free trial.
Get started
Install Feldr in under a minute. Detection and redaction run in your browser from the first prompt - no setup, no plaintext leaving your machine.
14-day free trial · From $4.20 per user / month · Built for SOC 2 Type II
We process limited personal data (like the email you share to join the waitlist) with your consent, in accordance with India’s Digital Personal Data Protection Act, 2023 (DPDPA) and our Privacy Policy. You can withdraw consent at any time.