Is your site AI slop?
Paste an address. We render the page, tell you what it is built with, look for builder fingerprints and stock component patterns, and quote every piece of evidence we find. Free, no signup, no full audit needed.
Only the AI check and what the site is built with. You can start the full audit from the result.
What we look at
Builder fingerprints
Lovable, v0, Bolt, Base44, Replit, ChatGPT Sites, Figma Make and a dozen newer builders generate a site from scratch and leave product markers in scripts, meta tags and asset hosts. Those count only where code lives, never in the text. A page that mentions v0 in a sentence was not built by v0.
Coding-agent residue
Claude Code, Codex, Cursor and similar tools edit a repository instead of generating a product. They leave instruction files, backup copies with the tool's name, "generated with" markers, and a recognisable signature in how the CSS was overridden. A fixed fingerprint list scores such a site zero. We look for the residue.
Stock component patterns
Forty named page elements, each weighed against pages built without AI. Some raise the odds: an accent-coloured word in the headline, one particular icon set, a dot-separated feature line, gradient text, numbered steps, three icon cards when they really are cards. Some lower them: customer logos, testimonials with faces, a four-column footer. The announcement pill above the headline, which almost everyone calls a tell, is neutral: designers reach for it just as often, so it does not count.
What the verdict means
- Confirmed
- A build artefact names the tool: a generator tag, a builder script, an instruction file served from the root. Right every time in our validation.
- Likely
- Strong stack signals, or a cluster of measured patterns with little authored work around them. Comes with a confidence number.
- Possibly
- Stock components were found. Designers use the same kits, so the verdict is capped here and no number is shown.
- No evidence found
- Nothing generated was found. This is not a certificate of human work: it came up on 9% of the AI-built sites we measured, and on about a third of the sites whose makers used a coding agent.
- Not measured
- The page could not be fetched or rendered, a bot wall answered instead of the page, or the page has too little content to measure (a single-canvas app, an empty shell).
How often it is right
Measured in October 2026 by the same engine that runs your scan, on sites whose origin we know for certain: some built with AI tools, the rest by people. Sites that refuse a scanner or could not be read are left out, not counted as clean. On sites built by people that were never used to set the weights, Confirmed never fired and Likely fired about once in fifty.
| Verdict | Measured |
|---|---|
| Confirmed, when we say it | correct 100% |
| Likely, when we say it | correct 88% |
| Confirmed or Likely, AI-built sites caught | 86% |
| Sites made with a coding agent | caught 36%, nothing found 30% |
| AI-built sites that came out No evidence found | 9% |
Sites whose makers said they used a coding agent (Claude Code, Cursor, Codex) are the hard case. About one in seven could not be read at all. Of the rest, the check caught about a third and found nothing on another third. An agent that writes a small site by hand leaves no builder fingerprint and often no public repository, so a clean result on that kind of site is worth little. We say it here so you know.
Tool by tool
| Tool | What it leaves behind |
|---|---|
| Lovable | A builder script, the badge, the default social image, tagged elements. |
| v0 by Vercel | A generator tag and images on the Vercel blob host. |
| Bolt | The builder host and a server header. |
| Base44, Replit, ChatGPT Sites | The app host in a technical slot, runtime token names, the one-line app shell; ChatGPT Sites also ships a Codex preview tag. |
| Figma Make | A flag in Figma's site runtime that says the page came from Make. Figma Sites, the design tool on the same host, counts as counter-evidence. |
| Other prompt-to-site builders | Manus, Emergent, Hercules, Rocket, Readdy, Anything, Wegic, Gamma, MiniMax, Macaly and Floot: their own scripts, badges and image hosts, which stay when the site moves to its own domain, and the publishing address each one uses for its users' apps. |
| Pasted ChatGPT, Gemini or Perplexity text | Citation markers the chat left in the HTML. |
| Claude Code, Codex, Cursor, Windsurf | Instruction files served from the root, backup copies carrying the tool's name, "generated with" markers, the override signature in the CSS. |
| Framer, Wix, Webflow | Counted as counter-evidence. They are site builders, not AI. |
What it will not tell you
- It never says a site was made by a human. It reports the evidence it found, and its absence.
- The free check reads one page, the one you give it. On the paid plans, a deeper scan through the API runs it on up to 20 pages across the site and lists what repeats.
- A quarter of AI-built sites are empty shells filled in by JavaScript. We render them, and the report says when a static fetch would have seen nothing.
- A well-executed site on shadcn or Tailwind lands in Possibly. That is the design, not a bug.
- It is built for websites: landing pages, marketing sites, product pages. Games and single-canvas apps show it almost nothing, and it says so rather than calling them clean: on games from a vibe-coding jam, more than half came back as not measured, and it caught almost none of the rest.
- A verdict is an automated estimate from public signals, not a statement of fact about a site or its authors.
If we got it wrong
Every report has two buttons under the verdict: wrong, and right. What you send goes into the next corpus run, and the numbers on this page change only when a run changes them.