Loading page content
Scores text against four measurable patterns that show up disproportionately in AI-generated writing: sentence-length uniformity, characteristic buzzwords, passive-voice density, and vocabulary diversity. It reports a likelihood, not a verdict.
Analyze text for patterns commonly associated with AI-generated content: sentence uniformity, overused AI buzzwords, passive voice, repetitive structure, and vocabulary richness. 100% client-side, no text is sent anywhere.
Be clear about what this can and cannot do. No detector, including the commercial ones, can reliably determine authorship. The published false-positive rates are high enough that using any of them to accuse someone is indefensible: non-native English writers and technical writers with deliberately uniform style get flagged constantly.
Where it is genuinely useful is as an editing tool on your own drafts. Sentence-length uniformity is the strongest signal and the easiest to fix: human writing varies rhythm, alternating long sentences with very short ones. Flat, uniform sentence length reads as machine-generated even when it is not, and breaking it up improves the prose regardless of who wrote it.