Deckrd: KI-Erkennung

Erkennen Sie KI-generierte Nachrichten in Ihren Unterhaltungen

Deckrd — AI Detection for Your Conversations Know who you're really talking to. Deckrd silently analyzes chat conversations to detect AI-generated messages, alerting you when your conversation partner may not be human. HOW IT WORKS • Automatic detection on Discord, WhatsApp, Messenger, LinkedIn, and X DMs • 5 behavioral detectors analyze timing, language, coherence, style mimicry, and persona consistency • Floating widget appears when AI probability crosses your threshold • Browser notifications for high-confidence AI detection PRIVACY FIRST • All analysis happens locally in your browser • Your messages never leave your device • No message content is stored — only anonymous scores • Optional server analysis sends only anonymous signal data, never message text (future release) CUSTOMIZABLE • Adjust detection thresholds with simple sliders • Choose when the floating widget and notifications appear • Works on any chat platform with smart heuristic fallback Free to use. Pro tier coming soon with AI consensus deep analysis. Deckrd v0.8.0008 — What's new - Try Deckrd before you sign up. The popup no longer requires an account up front. Install it, watch the boot animation, and start scoring chats straight away. Sign-in is still available if you want it (Account tab) and is required for founder benefits. - Now on Firefox. Our Mozilla add-on listing is live, so Firefox users can install Deckrd directly from addons.mozilla.org. - Smarter Help button. Every tab in the popup now has a ? that opens the matching help article — including troubleshooting guides for the most common "why isn't this working?" moments. - Listing name updated. The extension is now Deckrd: AI Detection (was Deckrd — AI Detection). We removed em-dashes across the popup, listing copy, and emails as a small human-touch — the em-dash has become one of the most reliable tells that a piece of writing came from an AI, and we'd rather not be mistaken for one of the things we're built to catch. Fixes - Paste-to-Analyze accuracy. Polished human prose that was occasionally scoring 100% AI now lands correctly in the inconclusive band when the signals are genuinely mixed, and confident AI prose still scores AI. A 200-word minimum keeps short paragraphs from triggering false verdicts. - Various reliability fixes in the live-monitoring pipeline so verdicts update promptly as new messages arrive and survive page navigation cleanly. Privacy No new permissions. Detection still runs entirely on your device — no message content ever leaves your browser.