Verdah

Scores LinkedIn posts for AI-written text as you scroll. Right-click any text anywhere to check it.

Half of LinkedIn reads like it came out of a machine. Verdah tells you which half. Each post gets a badge — AI, Human, or Mixed — plus the exact phrases that led to the call. You keep scrolling. It just tells you what you're reading. WHAT YOU GET - A verdict badge on each post: AI, Human, or Mixed - A confidence level on every call, and a badge that gets quieter when the call is less certain - The exact phrases from the post that drove the score, quoted back to you - Right-click any text on any website to check it — no copying, no extra tab - A summary panel showing how much of a feed is AI - Author check on profiles: what share of someone's visible posts scored as AI - Disagree with a call? Mark the right verdict yourself in one tap YOU CHOOSE HOW STRICT IT IS A recruiter screening candidates wants almost no false accusations. Someone decluttering a feed wants to catch more. Three settings — Cautious, Balanced, Aggressive — and verdicts on screen update the moment you change it. WRITING IN A SECOND LANGUAGE IS NOT AI This is the part most detectors get wrong. Missing articles, formal textbook phrasing, idioms translated a little too literally — these get read as "machine-like" when they are the opposite. They are evidence a real person wrote it. Verdah treats them that way on purpose. Across ten human-written posts using Spanish, Hindi, German, French, Chinese, Arabic, Polish and Japanese language patterns, Verdah flagged none of them as AI. LinkedIn is global, and accusing someone of faking their own writing because English is their second language is not acceptable. HOW ACCURATE IS IT Honestly: partially, and we would rather tell you than round up. Measured against 100 labelled posts (50 AI-written, 50 human-written), Verdah correctly flagged 48% of the AI posts — and did not falsely accuse a single human writer. That's the tradeoff we chose. Verdah misses some machine-written posts. What it will not do is tell you a real person is a bot. When Verdah says AI, it is almost always right, and that's the number worth trusting. No AI detector is reliable enough to be a verdict on a person. Treat every badge as a reason to read more closely, never as proof. FREE - Scans your home feed - 50 posts a day - AI / Human / Mixed with confidence and evidence - Right-click check on any site - Correct any verdict PRO - Scans every profile, company page, group, and post search - Unlimited scans - Filter any feed by verdict - Author check on profiles - Shareable feed summary card - Feed composition tracked over time Verdah analyzes only the text of posts on LinkedIn, plus any text you select yourself elsewhere. It does not collect your identity, sell data, or track you across the web. Your feed history stays on your device. See the privacy policy at https://verdah.com/privacy.html Verdah is an independent tool and is not affiliated with, endorsed by, or connected to LinkedIn.