AI Website Detector
Paste any public web address and our free AI Website Detector fetches the live page, then weighs more than eighty signals across the build platform, markup, typography, imagery and writing style. You get one score from 0 to 100, a plain verdict, a confidence figure, and a full evidence ledger showing exactly which findings pointed toward AI and which pointed toward people.
How to check if a website was built with AI
Finding out whether a website was made by an AI website builder takes under a minute.
Paste the web address
Type or paste any public website address into the box above. You don't need the https:// part, and there's no sign-up.
The detector reads the live page
It fetches the page just like a browser and weighs more than eighty signals across the build platform, code, typography, imagery, metadata and writing style.
Read the score and verdict
You get a 0–100 score, a plain-English verdict from hand-built to AI-generated, and a confidence figure that shows how strong the evidence is.
Explore the evidence
Open the evidence ledger to see exactly which findings pointed toward AI and which pointed toward people, ranked by how much each one moved the score.
Common signs a website was made with AI
No single clue proves it, which is why the detector weighs many signals together. These are the patterns it pays most attention to.
- Builder fingerprints in the code, such as generator tags and platform scripts from AI website builders.
- A templated layout: hero, three feature boxes, testimonials and a call to action in the same predictable order.
- Generic headlines and copy that could describe almost any business in the industry.
- Stock-style or AI-generated imagery with no real photos of the team, products or premises.
- Thin business details: missing address, registration or named people behind the company.
- Little accessibility care, such as missing image descriptions or unlabelled buttons.
Who uses an AI website detector
Knowing how a website was built helps people make better decisions about it.
Business owners
Check what you're really getting before you pay for a website, or confirm that the custom site you commissioned wasn't simply generated.
Agencies and freelancers
Benchmark competitor and prospect websites, spot quick-build sites that need a rebuild, and show clients the difference real craft makes.
Buyers and investors
Add a quick technical check to due diligence when buying a website, domain or online business.
Designers and developers
See how AI builders structure pages and learn which signals make a site feel templated, so your own work stands apart.
Marketers and SEO teams
Find out whether thin, generated pages might be holding a site back in search and in AI answers.
Researchers and educators
Study how quickly AI-generated websites are spreading and teach students how the web is built today.
What makes this AI website detector different
Evidence, not guesswork
Every verdict comes with the signals behind it, so you can see why the score landed where it did.
Confidence you can read
A separate confidence figure tells you when the evidence is strong and when it's mixed.
80+ signals in 12 groups
Platform, hosting, code style, accessibility, metadata, imagery, trust signals and writing style are weighed together.
Free and private
No sign-up and no tracking of what you scan. Share any report with a simple link.
AI website detection: common questions
What does an AI website detector actually check?
This AI website detector fetches the live page and weighs more than eighty observable signals across twelve groups: the build platform, hosting and infrastructure, leftover AI artefacts, markup and code style, accessibility care, metadata quality, imagery sourcing, business trust signals, writing style, page structure, typography and the visual design system. It recognises the fingerprints of AI website builders such as Durable, 10Web, B12, Lovable, Bolt, v0, Butternut, Mixo, Zyro and Jimdo Dolphin, and separates them from visual builders like Wix, Squarespace, Webflow and Elementor and from genuine developer stacks such as Next.js, Laravel, Astro and custom WordPress themes.
How accurate is the AI detection score?
The score is a weighted probability estimate from observable evidence, not a certainty. When a site declares an AI builder in its generator tag or ships an AI builder badge, the verdict is close to definitive. When the evidence is purely stylistic — phrasing, typography, layout patterns — it is an informed indication. A carefully edited AI-built site can read as human, and a template-heavy agency site can read as AI. That is why every result shows its confidence figure and the full evidence ledger rather than a bare number.
What score counts as an AI-generated website?
The scale runs from 0, meaning entirely human, to 100, meaning entirely AI. Below 25 the site reads as hand-built. From 25 to 41 it is likely hand-built. From 42 to 51 the evidence is genuinely inconclusive and the tool says so instead of guessing. From 52 to 64 the site looks human-built with AI-assisted copy or sections. From 65 to 79 it is likely AI-generated, and from 80 upwards the evidence is strong.
Can it detect AI-written content on a human-built website?
Yes, and that case is common. The writing-style group looks for LLM stock phrasing, unusual em-dash density, the "not just X, but Y" construction, rule-of-three list phrasing, unnaturally uniform sentence rhythm and low vocabulary diversity. A hand-coded site with AI-written copy typically lands in the AI-assisted band: human platform signals pull the score down while the language signals push it up.
Why is a monospace font treated as an AI signal?
Code-generating models reach for the same small set of typefaces on almost every brief. Monospace faces such as JetBrains Mono, IBM Plex Mono, Space Mono and Geist Mono applied to body or interface text — rather than to code samples — are a reliable tell, as are stock pairings built from Inter, Manrope, Space Grotesk or Plus Jakarta Sans. Monospace used properly for code blocks is scored as neutral context, and a licensed foundry typeface or a self-hosted webfont counts in the other direction, because someone chose it deliberately.
Does it work on password-protected or JavaScript-only sites?
No. Only publicly reachable pages can be analysed, and the scanner reads the server-rendered HTML rather than executing JavaScript. A single-page application that renders everything client-side will return fewer content signals, so the confidence figure drops accordingly. Internal, local and private network addresses are blocked outright for security reasons.
Will Google penalise a website built with AI?
Google judges content by helpfulness and quality rather than by how it was produced. There is no penalty for using AI as a tool. What does get penalised is thin, unoriginal, mass-produced content built to game rankings — which happens to be what unedited AI output usually looks like. If a scan flags your own site, treat the evidence list as an editing checklist rather than a verdict on your search rankings.
How do I make an AI-generated site read as genuinely hand-built?
Work down the evidence list. Replace boilerplate section headings with copy specific to the business, cut the stock LLM phrasing, and add first-person detail, real dates and named people. Swap placeholder and stock imagery for real photography, write meaningful alt text, publish working contact details, and fix dead placeholder links. Choose a typeface deliberately instead of keeping the default, and set proper titles, meta descriptions and structured data. Each fix removes a signal and moves the score.