AI content detector for articles and live pages
Paste the address of a published page and we will pull out the article text and check it. Useful for reviewing freelance submissions, auditing an existing blog, or seeing how a competitor's content was produced.
Your report will appear here
Review copy before it goes live
If you commission writing, you are entitled to know how it was made. Run a draft through the detector before you pay for it or publish it. The sentence highlights make the follow-up conversation specific: you can point to the paragraphs in question instead of making a general accusation.
A result in the Uncertain band is common for writers who use AI for outlines or first drafts and then edit heavily. Whether that is acceptable is a policy question for you and the writer, not something a tool can settle.
AI content and search rankings
Google has said publicly that it rewards helpful content however it is produced, and that using automation to mass-produce pages aimed at manipulating rankings violates its spam policies. In other words, AI involvement is not what gets a page demoted; thin, unoriginal content is.
So treat a high AI score on your own pages as a prompt to check quality. Does the piece contain first-hand experience, original data or a point of view? The pattern list is a quick read on how generic the writing sounds.
Checking pages by URL
The URL checker fetches the page, strips navigation, sidebars, tables and footers, and analyses the main article text. Pages that render their content with JavaScript, sit behind a login, or block automated readers cannot be fetched; for those, copy the text and use the Text tab.
How the AI detector works
An AI detector is a classifier that estimates the probability that text was written by a language model rather than a person. It works by measuring statistical patterns in the writing, not by tracing where the text came from.
Give it something to read
Paste text, drop in a PDF or Word file, or enter the address of a web page. Documents are opened in your browser, so the file itself never leaves your device.
The text is scored
A detection model trained on human writing and on output from AI systems rates the whole text and each sentence for how closely it matches machine writing.
You see the evidence
The report marks every sentence, lists the writing patterns found, and tells you how much confidence the result deserves.
How accurate is AI detection, honestly?
AI detection is accurate enough to raise a question, but not accurate enough to prove an answer. The best detectors catch most unedited AI text with few false alarms, but accuracy drops sharply when text is paraphrased, lightly edited, or written by a non-native English speaker.
Key takeaways
- Accuracy claims of 99% come from the vendors’ own benchmarks.
- One 2026 test of five detectors put the top two at 72% and 74% overall accuracy.
- False positives fall hardest on non-native English writers.
- A score is a probability estimate, not evidence of misconduct.
Reading the score
| Score | Verdict |
|---|---|
| 0–14 | Human-writtenLittle or nothing resembles AI writing. |
| 15–34 | Likely human-writtenMostly reads as a person, with a few AI-like passages. |
| 35–69 | UncertainMixed signals. Not evidence either way. |
| 70–89 | Likely AI-generatedMostly reads as AI, possibly edited by a person. |
| 90–100 | AI-generatedStrong, consistent AI signals throughout. |
A score in the Uncertain range is reported as Mixed when the sentences back that up, with at least 25% of the words in AI-like sentences and at least 25% in human-like ones.
Supported languages: English, French, Spanish, Portuguese, German, Dutch, Polish, Romanian, Italian and Simplified Chinese.
AI Content Detector: common questions
Can I check a whole site at once?
Not here. This tool checks one page at a time. Start with your highest-traffic pages and the ones you did not write yourself.
Does Google penalise AI-generated content?
Google's published guidance focuses on quality and intent, not on the method of production. Scaled, low-value content can be treated as spam whether a person or a model wrote it.
Why did the URL check fail on my page?
The most common reasons are content loaded by JavaScript after the page opens, a login or paywall, or a firewall that blocks automated requests. Paste the text instead.
Does it work on product descriptions and short copy?
Short text gives weak results. Anything under about 100 words is marked low confidence; combine several descriptions into one check for a better read on a writer's overall style.