/compare · positioning

How Slop Detector compares

Where Slop Detector sits among design-quality and AI-detection tools, and why its methodology is different.

01the short version

One fixed yardstick, not a moving model

Most "is this AI?" tools are probabilistic ML classifiers: they output a confidence that something was machine-generated, and that confidence shifts as the model is retrained. Slop Detector works the other way. It is a deterministic fingerprint: a fixed catalogue of CSS and copy tells, each with a fixed weight, evaluated against a page's live computed styles in real headless Chromium. The same page always yields the same score. No model, no randomness, so the output is auditable, reproducible, and safe to gate CI on.

02methodology comparison

How the approaches differ

Methodology comparison across Slop Detector, ML AI-detectors, and Lighthouse/a11y tools
DimensionSlop DetectorTypical ML AI-detectorsGeneric Lighthouse / a11y
OutputDeterministic 0–100 weighted fingerprintProbabilistic % confidencePerf / a11y / SEO scores
ReproducibleYes, same page, same scoreNo, drifts with retrainingMostly
What it measuresAI-design + copy slop tellsGenerated-vs-human likelihoodTechnical quality, not aesthetics
EngineReal Chromium, computed stylesText / pixel modelsReal Chromium
Auditable rulesYes, open catalogue at /api/patternsOpaque weightsDocumented audits
AEO axis (AI-readability)Yes, built inNoPartial (SEO only)
LicenseOpen source (MIT)Usually closedMixed
Agent interfacesAPI + CLI + MCPRareRare
03why deterministic matters

What a fixed score buys you

04the research behind it

Where the weights come from

The pattern weights derive from Adrian Krebs's April 2026 study of 1,400 Show HN submissions, plus Meng To's gradient-avatar tell. The catalogue is versioned (DEFINITIONS_VERSION) and served live at /api/patterns.

05when to use which

Pick by the question you're asking

06try it

Run a scan

Web: slop-detect.com · CLI: npx slop-detect <url> · MCP: slop-detect-mcp · API: /openapi.json · Source: GitHub