FakeScan – AI fake review detector (Fakespot is dying)
Replaces Fakespot's shutdown gap, but ReviewMeta already does this.

Paste any Amazon product URL → AI analyzes the reviews for suspicious patterns (review clustering, generic language, incentivized reviews, timing anomalies) → gives you a trust score 0-100 with specific red flags.
Tech stack: Next.js, Groq API (Llama 3.3 70B for analysis). No login, no data collection, completely free.
Would appreciate any feedback on the detection algorithm or UX.
Replaces Fakespot's shutdown gap, but ReviewMeta already does this.
Free Fakespot replacement, but ReviewMeta and browser extensions already exist.
Short, 15-second recorded takes plus an AI verification step is a smart twist on noisy written reviews — it's compact, snackable content that could surface honest signals. The landing page nails the messaging and onboarding hook (Google sign-in, one-button record), but it leaves key questions unanswered: how reliable is the 'AI evaluates' authenticity check, and who funds the payouts?
Forensic report on one video, not a reusable detection tool anyone can run.
Calls out PSI cosplay by checking Set-Cookie on HTML and cache header games.
Detection logic is scientifically flawed and easily bypassed by modern tokenizers.