VeriTextDetect AI writing
with explainable precision.
Sentence-level analysis, adjustable sensitivity and your own classification rules — built for educators, editors and hiring teams.
Trusted by teams at
Everything you need to judge authorship fairly.
See exactly which lines look generated
Every sentence gets its own score and the signals behind it, so you can make informed decisions.
I wrote this on the train home, half asleep. Furthermore, it is crucial to consider the broader implications of this transformative landscape. Anyway, that's my take.
Adjustable sensitivity
Five thresholds from very lenient to very strict.
Custom rules
Ignore quotes, citations, or set your own flag threshold.
Model profiles
Compare against GPT, Claude, Gemini and open-model styles.
Explainable
Signals for and against, plus clear limitations.
File upload
Drop in a .txt file and scan in seconds.
Five signals. One clear report.
Add any text — essays, articles, cover letters.
Pick sensitivity, categories and rules.
Predictability, variation, patterns and more.
Explore sentence-level results and evidence.
Simple plans for every team
Questions, answered
Is the score proof of AI use?+
No. It is a model estimate. Use it alongside other evidence and conversation.
Is my text stored?+
No. Text is analyzed in memory and discarded after the report is generated.
Does grammar correction count as AI?+
Not by default — you decide in Settings under “What counts as AI”.
Why is my result inconclusive?+
Very short or ambiguous text doesn't carry enough signal for a reliable call.