Paste your essay into the checker on this page, press check, and you get a score from 0 to 100 with one of three readings: Reads as AI-generated, Borderline, or Reads as human-written. The run takes seconds, the text needs to be at least 65 words, and a check costs one credit whatever the length, so a two-page essay and a single paragraph cost the same. The free allowance is ten credits a day per network, with no account, no login, no card and nothing to verify, which is ten full checks a day. Read the result as a description of the draft rather than a verdict on you, because that is what the number is. It describes how the writing reads on the surface: how predictable the phrasing is, how even the sentence rhythm is, how often stock constructions turn up. It cannot report who typed the words, and no detector anywhere can, because text carries no record of its own authorship. That distinction matters more than any single score, and this page works through it properly: what the score actually means, how much of the essay to paste in one run, why honest essays still get flagged, and what to do with the result while you can still edit. The order matters too. Checking before you submit is editing your own draft. Checking after you submit is answering somebody else's question about it, and those are different jobs.
Every run returns the same two things. The first is the number, from 0 to 100, where higher means the text carries more of the surface features these systems respond to. The second is a plain reading of that number in one of three bands. Reads as human-written means those features are largely absent. Reads as AI-generated means they are present in quantity. Borderline means the reading is genuinely unresolved, and the honest way to treat it is as neither result rather than as a pass.
The floor and the ceiling are both fixed. A check needs at least 65 words, because a reading taken from less text than that is close to noise, and a single run takes up to 12,000 characters, which is roughly 2,000 words. Whatever you paste inside that range costs one credit, so there is no penalty for checking a long essay and no reason to trim it to save money.
The number describes style, not authorship. Nothing inside a document records who typed it, so every detector, this one included, is reading how the sentences behave and inferring from that. A high score is a description of the writing, not evidence about the writer. It is also not a forecast of the number your school's software will show. That is a different model, with thresholds somebody local chose and a retraining schedule of its own, and detectors can disagree about the same paragraph.
The band is the part to act on, and it deserves a strict reading. Borderline is not a pass and not a fail; it is a reading that genuinely did not resolve, and the honest move is to treat it as unresolved rather than to hope. Reads as AI-generated on your own essay is a note about the draft, which is exactly what you want from a tool you run before submission.
Paste the whole essay if it fits. One run takes 12,000 characters, roughly 2,000 words, and most single assignments land under that. The floor is 65 words, because a reading drawn from less text does not mean much. If you are a few words short, include the paragraph around the passage rather than checking a fragment on its own.
Above 2,000 words, split at your own section breaks rather than mid-argument and check the parts one after another. A check costs one credit at any length, so a 5,000-word chapter is three runs and three credits out of the ten free ones, and you get a clearer reading of each section than one blended number would give you.
Human writing gets flagged, and not at random. Researchers at Stanford HAI (Liang et al., 2023) ran TOEFL essays written by non-native English speakers through seven detectors and found 61% falsely flagged as AI-generated. Every one of those essays had a human author. The writing that gets caught is not sloppy writing; it is the opposite. Plain, orderly, correctly punctuated prose, organised to a template, is the profile these scores respond to.
That lands hardest on writers working in a second language and on anyone who writes the way school taught them to, because the taught register is precisely the even, formal register that reads as machine-made. If that describes you, a high score on your own draft is a property of the style you were taught, not a finding about you. The page for ESL writers goes through this in more detail, and the false positives page covers who gets flagged and why.
The patterns are specific, and most of them are habits school taught you. The opener that announces a topic is important without saying anything about it. The pivot that manufactures a contrast the sentence never needed, as in "not just a tool, but a transformation". The tidy three-item list where two items would have done. The conclusion that opens by declaring something is clear. Hedges stacked two and three deep, as in "it could be argued that this may potentially suggest".
Rhythm counts as much as vocabulary. A paragraph in which every sentence lands within a word or two of the same length reads machine-made to these systems whoever wrote it, because real drafting is uneven: people write a long sentence, then a short one, then a clause they meant to cut and kept. The registry of 44 named AI writing tells highlights the exact phrase in your own text instead of scoring the document, and it is free and unlimited, so you can paste a draft into it as often as you like while you edit.
Do not start rewriting in a panic. Run the tell registry over the same text first and look at what fired. If the highlights cluster in one or two paragraphs, you have an ordinary editing job in front of you, and you can do it by hand in a few minutes. If almost nothing fires and the score stays high, the cause is usually plain, orderly, formal prose, which is a description of how you write rather than a fault in it.
For the passages that genuinely read as machine-written, the humanizer rewrites every sentence you give it in one click. It takes up to 12,000 characters, roughly 2,000 words, per run, needs at least 25 words, and costs one credit per 50 words, so the free allowance covers around 500 words of rewriting a day, which is enough for the sections a check points at. Send the paragraphs that scored worst through it, then check the rewritten version here, and leave the writing that already worked alone.
A record helps more than editing does. Draft in something that keeps version history, such as Google Docs or Word, and keep your outlines and earlier files where they are, because copying the text into a fresh file leaves that history behind. The signed drafting record captures a writing session as it happens and seals it with an ECDSA P-256 signature anyone can verify, and it is free and unlimited. If an accusation has already been made, the falsely accused page has the questions to ask before you reply.
Yes. Ten credits a day per network, and a check costs one credit whatever the essay's length, so that is ten essay checks a day. No account, no card, no email address and nothing to verify. The registry of AI writing tells, the proofreader, the word counter, the readability check and the originality check are free with no limit at all.
No one can give you that number honestly. A threshold is chosen by whoever runs the software, not by the text. Read the band rather than the digits: human-written means the patterns are absent, borderline means the reading is unresolved, AI-generated means the phrasing is worth fixing before you hand the essay in.
Not necessarily. It is a different model with its own thresholds, retrained on its own schedule, and detectors can disagree about the same paragraph. This checker tells you how your draft reads on the features these systems respond to. It cannot tell you what another product will output.
12,000 characters per run, roughly 2,000 words, with a floor of 65 words. A longer essay goes through in sections, split at your own headings. The cost is one credit per run either way, so a long passage does not spend your allowance faster than a short one.
No. It means your text carries the surface features these systems score, and human writing carries them too. The Stanford HAI TOEFL finding is the clearest published evidence of that. Treat a high score as a reason to look at specific sentences, not as a verdict on you or your work.