An AI detector for publishers, editors and magazines

IsThisAiWritten is a free AI detector for publishers, editors and literary magazines. It screens submissions of any length, from a 2,000-word story to a full manuscript, without uploading anyone's unpublished work: paste or open a submission below. The report shows which chapters and passages read most like AI, so your readers know where to look first.

Why editors use it for submissions

• Free, with no sign-up. No account, no email and no credit card. No credits, no daily cap, no per-manuscript fee, no paywall and no premium tier.
• No word or character limit. A whole novel goes in as one check: a 208,000-word book has been analysed in one go.
• Nothing is uploaded. The check runs in your browser, so an author's manuscript never leaves your device.
• Submissions are never stored, shared, sold or used to train anything. We never receive them.
• Every word is scanned, never a sample, from the first page to the last chapter.
• A report that explains itself: an AI-likeness score, sentence-by-sentence highlights, a chapter view, style notes with one-click plainer wording, a hidden-character and look-alike-letter cleaner, and a narrative fingerprint for fiction.
• Opens .txt and .docx files right in the browser, which is how most submissions arrive.
• No ads where you paste text.

Built for a full submissions queue

A reading period can bring in hundreds of stories, essays and manuscripts. With no daily cap and nothing to pay per check, an editorial team can screen every one of them, including the ones nobody has doubts about yet. Everyone on the team uses the same page, with no seats to buy or accounts to share.

Long work is handled properly. Chapters are found from their headings, so a full manuscript gets a result for each chapter. Above 30,000 words the text is shown in pages of 5,000 words with a chapter jump menu, and partial results appear while the scan runs, with a cancel button if you want to move on. A chapter that scores well above its neighbours tells a reader exactly where to start.

How publishers can screen submissions with an AI detector

1. State your AI policy in your submission guidelines, including that you may screen with a detector.
2. Paste or open each submission in the box above. Keep chapter headings on their own lines so the chapter view can find them.
3. Look at the hidden-character notes and record anything the cleaner found.
4. Set aside any submission that comes back AI or Mixed for a second read.
5. On the second read, look at the passages the sentence map marks highest and judge the work on its merits.
6. File the report with the submission: download it as JSON, save it as a PDF or copy a short summary into your tracker.
7. If you're still concerned, write to the author, explain what you saw and ask about their process before you decide.

Confidentiality for unpublished work

Authors trust you with work that isn't public yet. Because the analysis runs in your browser, manuscripts are never uploaded to us or to a third party, and no copy of the text remains once you close the tab. That matters if your agreements with authors limit who can see a manuscript, and it means a rejected submission leaves no trace in anyone's database. Your IT team can confirm the behaviour in the browser's Network tab; the private AI detector page explains what to look for.

Narrative fingerprint and chapter view for fiction

For fiction, the report includes a narrative fingerprint: counts of features such as dialogue share, smell imagery and how often the narrator spells out what a scene means, shown beside human and AI base rates published in the StoryScope research (Russell et al., COLM 2026). It describes rather than judges and is never used in the verdict, so it gives an editor something concrete to discuss with an author even when nobody suspects AI. Details are on the long documents page, and how AI fiction differs explains the research behind it.

Hidden characters in submitted text

Zero-width characters and look-alike letters, such as a Cyrillic letter standing in for a Latin one, can turn up in submissions. Some arrive when text is copied out of web pages or other software; some tools insert them. The cleaner makes them visible and lets you copy a cleaned version, so the text you paste into your own production systems is the text a reader sees.