Sentence-length variation
How much sentence length changes within this sample.
Text evidence analyzer
Check text for AI writing.
Paste text or open a document for GPTZero AI screening and CouldItBe’s supporting writing observations. Consent is required before text is sent. You can also choose a local-only review.
What this tool can tell you
What it can doScreen text with GPTZero after consent and report local writing observations separately, including contrasting evidence.
What it cannot doProve who or what wrote something, calculate an AI-authorship probability, or replace provenance and writing-process evidence.
How to use these tools and read your results
Start here
Add text to check
Paste writing or open a document, then choose AI screening or a local-only pattern review.
Add your writing
Paste it below or choose one local file. A selected file is extracted in browser memory for your review before analysis.
No text handy?Illustrative AI-written sample, not an accuracy test.
Local analysis options (optional)
Use this when no more specific type applies.Get observations and measurements without assuming a genre.
Scan paper pages with a camera
Prefer not to upload? Review local patterns only.
Your evidence report
Results will appear here
AI screening finding
AI screening not run
Choose Check for AI writing and agree to send the text. A local pattern review alone does not classify AI authorship.
Ready when you are
Paste writing or open a document, then choose Check for AI writing or Review local patterns only.
Compare two drafts
Revision evidence
Compare how two drafts changed
Both drafts remain in browser memory. This describes changes; it does not identify a writer, editor, model, or tool.
Browser memory only · no upload · no retention · source text excluded from export
Research results and measurement glossary
Bounded research snapshot
What the paired pattern did in recent tests
These are aggregate pattern counts from fixed, bounded studies. They are not accuracy, probability, sensitivity, specificity, or proof of authorship. The rule was not changed after these results were reviewed.
Document typeTransformed synthetic samplesHuman reference samples
Essay5 / 6 showed the pair0 / 30 across 10 source groups showed the pair
Article5 / 6 showed the pair0 / 17 across 8 source groups showed the pair
Review6 / 6 showed the pair4 / 30; author grouping unavailable showed the pair
Important: Human reviews also produced the pattern combination. Editing, genre conventions, translation, templates, and individual style can create similar measurements. Review results therefore need especially cautious interpretation and provenance checks.
Privacy and methodology
What the measurements mean
Measurements describe visible structure and wording only. The paired-pattern review is document-aware, abstains where evidence is too limited, and must be considered alongside counterexamples and provenance.
Vocabulary distribution
How broadly words are distributed across moving passages.
Repeated phrases
Repeated three-word sequences; topics, quotations, and templates can create them.
Transitions and hedges
Linking and qualifying words that may reflect genre, editing, or style.
Template-shaped phrases
A small fixed list of common formulaic phrases, never a universal signature.
Citation-shaped patterns
Reference-like forms, not validation that a source is accurate.
Style shift
A change in average sentence length between halves of the document.
Evidence state
A review state—not a classification of who or what wrote the text.