Check AI text
Check If Text Is AI-Generated
Got a message, essay or post that feels a little too polished? Paste it and see what the signals say.
- No sign-up needed
- Sentence-level highlights
- Text never used for training
Minimum 80 words. Your text is analyzed securely and never used for AI training.
Privacy-first
Anonymous scans are never stored. Your text is never used to train AI.
Secure processing
Encrypted in transit, isolated per account, keys never exposed to the browser.
Fast analysis
Results in seconds, with sentence-level scoring for every scan.
Transparent scoring
Likelihoods and confidence levels — never an absolute verdict.
A clear answer to “did AI write this?” — with the nuance it deserves
Sometimes you just want to know whether a piece of text came from a chatbot. This tool gives you a straightforward likelihood score, then shows you the reasoning: which sentences look generated, and which writing patterns point that way.
Because AI detection is never certain, results are labeled in plain language — “likely AI-generated”, “mixed signals” or “likely human-written” — with a confidence level, instead of a misleading yes/no.
How it works
Three steps, a few seconds
- 1
Paste the text
Anything from a school essay to a LinkedIn post — at least 80 words.
- 2
Get a likelihood
An overall AI likelihood, human likelihood and detection confidence.
- 3
See the sentences
Hover or tap any sentence to see how strongly it reads as AI-written.
Use cases
Who uses it
Parents & students
Understand how writing might be perceived before it's handed in.
Hiring
Get a signal on whether application answers are personal — then ask follow-up questions.
Everyday curiosity
Check viral posts, reviews or emails that feel templated.
Limitations you should know
- A “likely AI” result is not proof — it means the text shares patterns common in AI output.
- Text you've polished with grammar or paraphrasing tools can look more AI-like.
- Mixed signals are common: many texts today are partly AI-assisted.
AI detection systems can produce false positives. Use results as one signal rather than definitive proof, and never as the sole basis for academic, employment or disciplinary decisions.
How we handle your text
- No training. Your text is never used to train AI models — ours or anyone else's.
- Anonymous = not stored. Scans without an account are analyzed and discarded.
- Private history. Signed-in scans are visible only to you, and can be disabled or deleted.
- Never public. Scans and reports are never indexed or shared.
FAQ
Frequently asked questions
How can I tell if text is AI-generated without a tool?
Look for uniform sentence lengths, generic transitions (“Furthermore”, “In conclusion”), vague claims without specifics, and an absence of personal detail. These are clues, not proof — and many good human writers use them too.
What does “mixed signals” mean?
The text contains both human-like and AI-associated patterns. It may have been drafted by AI and edited by a person, or written by a person using AI suggestions. Check the sentence highlights to see where each comes from.
Why do I need at least 80 words?
Short snippets don't contain enough statistical signal. Longer samples generally provide a more meaningful analysis; a few paragraphs work best.