Skip to content
ClaudeDetect
Language: English

How to tell if Claude wrote it

By Yang Zheng · Updated

Claude's text tends to use certain connective phrases much more than human writers, and to avoid ellipses, exclamation marks and parentheses. No phrase is proof, because people write this way too, but a cluster of them is a signal. The figures below come from Fileverity's training corpus, comparing fully AI-written English documents from the Anthropic family with human writing.

Phrases Claude uses more than humans

Multipliers show how much more often the phrase appears than in human writing, after matching the genre and source mix.

Phrases that set Claude apart from other AI

Many phrases are common to all AI text, so these compare Claude only with other AI families.

Structural markers

Against human writers, Claude uses:

Against other AI families, Claude uses em dashes 3.7× less often and "not X but Y" contrasts 3× less often. If a text is full of em dashes and "not X but Y" lines, that points away from Claude, not towards it.

Read these tells with care

Why a phrase list is not a detector

A list of phrases can be matched by anyone and defeated by a quick edit. Veread, the detection model behind this site, reads far more than phrases: how sentences are built, how the text moves from one idea to the next, rhythm and structure across the whole text. It works across seven languages and shows which passages carry the signal. In published tests it caught 98.4% of fully AI-written Claude text and wrongly flagged 0.5% of human-written text; see the accuracy figures.

Check a text yourself

Paste at least 100 words into the Claude AI detector to see the AI verdict, the marked passages and the style similarity to Claude. To compare all seven model families, see the guide on how each AI model writes.

Questions and answers

What are the signs that Claude wrote a text?

In English, phrases such as "far more", "yet the", "rather than" and "tends to" appear much more often than in human writing, and the text uses fewer ellipses, parentheses, exclamation marks and semicolons. These are tendencies, not proof.

Do em dashes show that Claude wrote it?

Not for Claude. In the training data Claude uses em dashes 3.7 times less often than the other AI families, so they are a weak clue for this family.

Can humans write like this too?

Yes. Every phrase here is ordinary English that people use. A single phrase proves nothing, and the signal comes from many tendencies together.

Is this the same as the Claude watermark?

No. These are style tendencies. The watermark is a hidden statistical mark that only approved organisations can check. See Claude watermark status.

Can I check a text automatically?

Yes. ClaudeDetect reads the whole text and shows writing-style similarity to Claude and other families.