Catalog copy checks
AI Product Description Detector for Listing Copy
Paste a marketplace listing, product page, or catalog field into this AI product description detector. Slop or Not checks the English copy for language patterns associated with LLM output, then returns a probability for review. Online, the pasted text first goes to Numen's server for a hidden-character scan that runs in memory and stores nothing. The separate AI check runs on Numen's private Mac server. The iPhone, iPad, and Mac apps run both checks on-device.
Catches 99.5% of AI text at a 5% false-positive rate, scored by RAID, the public benchmark, not by us.
Paste a paragraph or a whole thesis. The iPhone and Mac apps have no word cap and no monthly word budget.
- Paste English textSchool essays, product reviews, captions, articles, and social posts up to 20,000 characters.
- ResultA probability verdict, AI score, and readability analysis.
- PrivacyChecked on Numen's private Mac server and never passed to an outside AI company. For text that stays on your device, use the app.
What it checks
How Does an AI Product Description Detector Read Listing Copy?
Generic benefits that are not tied to the product specifications
Repeated sentence structures across features and selling points
Smooth explanatory phrasing around facts that do not naturally connect
Good Uses
- Checking seller copy before a marketplace listing goes live
- Triaging catalog entries that need disclosure or editorial review
- Comparing a product claim with the specifications and source materials
Limits to Know
- Specification lists repeat nouns and measurements in ways that can resemble generated copy
- Brand templates and SEO formulas deliberately standardize human-written listings
- Translations and very short descriptions leave less reliable language evidence
FAQ
AI Product Description Detector Questions
Does this prove a seller used AI?
No. The result describes the English wording, not the seller's workflow. A person can write formulaic copy, and AI-assisted text can be heavily edited. Review the listing history and source materials before drawing a conclusion.
Why can product specifications look AI-written?
Specifications repeat model names, measurements, and attribute labels. That regular structure gives a text detector less natural prose to evaluate and can raise uncertainty.
Can I check translated or very short listings?
The text detector supports English. Machine translation and short catalog fields can distort the writing patterns it reads, so use longer original English copy when available.
What happens to the listing text online?
The pasted text first goes to Numen's server for a hidden-character scan that runs in memory and stores nothing. The separate AI check runs on Numen's private Mac server. The iPhone, iPad, and Mac apps run both checks on-device.
Run the Next Check on Your iPhone or Mac
The Slop or Not app checks images and text on-device, so nothing you check ever leaves your device.
More from Numen
Three more apps that run on your device. None needs an account.
Private LLM
A Local AI chatbot for uncensored open-source models that runs offline on iPhone, iPad, and Mac. Private LLM uses OmniQuant and GPTQ quantization tuned per model, so its 3-bit models match the 4-bit models other apps ship.
Clean Links
Most tracking now hides behind link redirects. Clean Links unwraps short links and strips every tracking parameter from a URL before you share it, on iPhone, iPad, Mac, and the web.
Private Diffusion
Run the latest frontier image models on your iPhone, iPad, and Mac. Private Diffusion trains each one with quantization aware distillation (QAD), so the small model keeps the quality of the full size one.
Related checks
Compare Related Detector Workflows
AI Text Detector
Check whether writing looks AI-generated with Slop or Not. Paste text online for a quick check, or use the iPhone and Mac apps on-device.
ChatGPT Watermark Detector
Check text for the hidden characters ChatGPT leaves behind, like the U+202F narrow no-break space, and read the writing itself with a RAID-scored detector.