Drop in your link.
We open the page in a real browser and capture the first three screens, styles, and visible copy.
AI slop detector + website design feedback
Find generic UI, vague copy, and the AI slop holding your website back. Get specific design fixes and a prompt for your coding assistant.
THE PUBLIC SCAN BOARD
Real scans, open reports. Find a little inspiration for your next fix.
Loading public reports…
Skip the guessing. Go from a link to a concrete next step.
We open the page in a real browser and capture the first three screens, styles, and visible copy.
Get a pattern match score, the strongest signals, and a suggested fix for every match.
Copy a prompt built from your report into your coding assistant. Keep the good parts. Fix what’s generic.
A specific headline. A palette with a reason. A layout that fits the content. Small choices make a site feel like it belongs to someone.
Illustrative redesign. SlopFix gives suggestions; it doesn’t edit your website.
34 patterns across five categories. Open any check to see exactly what counts.
Read the complete 34-pattern checklist, including criteria and fixes.
The same default indigo-to-violet gradient (around #6366f1 to #a855f7) is used as a template accent on prominent buttons, glows, or hero backgrounds. Do not count a gradient with a different, clearly chosen palette.
Suggested fix: Pick one accent with a reason behind it and use it flat.
Visible heading text itself is filled with a gradient. Do not count gradients elsewhere on the page.
Suggested fix: Set headings in one solid color and build hierarchy with size and space.
A near-black blue page uses decorative spotlights, colored glows, or gradient card surfaces to signal generic premium dark mode. A dark theme by itself is not this tell.
Suggested fix: Hold one flat background and separate surfaces with a hairline.
The page repeatedly uses an amber, orange, or stone wash on a soft beige base as a generic cozy palette. One restrained warm brand accent is not enough.
Suggested fix: Use a neutral base and one restrained warm accent.
Several unrelated blue, amber, green, or red tinted boxes appear together like a default semantic palette. Do not count a restrained, coherent brand palette.
Suggested fix: Grow any extra colors out of your one palette, or drop them.
A sans-serif headline switches one emphasized word to an oversized or display serif italic for stock dramatic contrast. A consistent editorial type system is not this tell.
Suggested fix: Keep one voice per headline; emphasise with weight or a line break.
A software, developer, or SaaS product uses a high-contrast display serif as a generic premium signal in its hero or UI. Do not count a serif that fits a clearly editorial product and voice.
Suggested fix: Choose a face you can defend for this product, not the default of premium.
Tiny uppercase, letter-spaced labels repeat above many section headings and mostly restate their heading. One label that adds a category, date, or other useful context is not this tell.
Suggested fix: Delete kickers that repeat their heading; let scale introduce sections.
A long marketing sentence, around ten or more words, is set at display size and spans multiple lines in the hero. A short headline followed by a normal-size subline is not this tell.
Suggested fix: Make the big line a few words and put the rest in a normal-size subline.
The type system relies on generic, ubiquitous UI or display fonts as an unconsidered default, with no context-specific typographic choice. A popular font alone, or a purposeful combination, is not sufficient evidence.
Suggested fix: Try a few faces with your own copy and keep the one you can explain.
A terminal or code window is used as decorative tech styling even though it shows no real product output or useful code. A genuine, relevant code example is not this tell.
Suggested fix: Keep monospace for code and use terminal styling only where it serves the product.
Copy repeatedly uses stock symmetrical contrasts such as 'not X, but Y', formulaic three-part punchy lists, or excited claims without concrete nouns, numbers, or consequences. One em dash alone is not enough.
Suggested fix: Write one specific sentence with a real number, noun or consequence.
Generic hype words such as unlock, elevate, seamless, effortless, supercharge, or powerful recur without saying what the product actually does. One ordinary use of a word is not enough.
Suggested fix: Replace each hype verb with what the product actually does.
The main headline is portable marketing language that could advertise many unrelated products and names no audience, concrete job, or specific outcome. A short but product-specific headline is not this tell.
Suggested fix: Say who it is for and what changes for them, in their words.
Em dashes recur as a default rhythm crutch, especially in short marketing copy. Do not count one or two dashes used where they clearly improve a longer sentence.
Suggested fix: Use a period or a comma. In short copy, use no dashes.
Decorative emoji repeatedly lead headings, buttons, or bullets in place of a clear visual or verbal choice. A single meaningful status symbol is not this tell.
Suggested fix: Cut decorative emoji; keep one only where it carries information.
Copy repeatedly tees up an ordinary claim with phrases like 'what nobody tells you', 'the part everyone misses', or 'here is the uncomfortable truth'. A real sourced finding is not this tell.
Suggested fix: Cut the setup and make the claim on its own.
A prominent row presents contextless or implausible headline metrics as proof without a source, method, time period, or explanation of what was measured. Do not assume a number is invented merely because its source is offscreen.
Suggested fix: Show one number you measured and say where it came from.
Repeated prominent calls to action use generic labels such as 'Get started', 'Learn more', or 'Try for free' without naming what the visitor gets. One conventional button is not enough.
Suggested fix: Name the first thing the visitor gets when they click.
Decorative status pills such as 'New', 'Beta', or 'Popular' recur without a real, current status they communicate. One factual release or availability badge is not this tell.
Suggested fix: Show a badge only for real, current status.
A bright dot has a large pale halo or pulse and sits beside generic 'online', 'ready', or 'live' marketing copy without a meaningful changing state. A small flat dot for a real status is not this tell.
Suggested fix: A flat dot plus a word, and only when something is actually live.
Repeated features each get a generic line icon inside an identical rounded-square tile, used mainly to fill a grid rather than explain the feature. One meaningful icon is not enough.
Suggested fix: An icon must carry meaning or go. A label and one sentence is enough.
Many icons sit inside low-opacity backgrounds tinted to match each icon's own hue, making a grid of soft colored squares. A coherent opaque brand surface is not this tell.
Suggested fix: Let the icon inherit the text color, with no container.
The interface repeatedly uses maximum-radius capsule shapes and/or translucent cards with visible backdrop blur as a decorative style preset. Normal small-radius buttons or cards alone do not count.
Suggested fix: Hold one small radius site-wide and use solid surfaces.
Small cards or icons carry a very wide, diffuse, low-opacity shadow that greatly exceeds their size, often alongside a border or colored glow. A restrained shadow matching a real elevation is not this tell.
Suggested fix: Use a tight, colorless shadow, or only a hairline.
A thick colored stripe on a rounded pale card is repeated across feature lists, rows, or notes as decoration. One real warning or note callout is not this tell.
Suggested fix: Let a list be a list; save callouts for one or two real asides.
The visible mark looks like crude placeholder vector art, such as a rounded square with a face or a mascot made from primitive shapes. Do not infer that a logo was AI-made from style alone.
Suggested fix: Get a real mark from a designer, or refine one until it is crisp.
The opening follows a generic landing-page recipe, such as an eyebrow or announcement pill, centered oversized headline, generic subline, paired buttons, and decorative gradient, without product-specific proof or interface. One centered hero element is not enough.
Suggested fix: Start with what only your product can show above the fold.
Three equal feature cards use generic icon, heading, and short-description content, giving unrelated features identical emphasis instead of showing the product doing something specific. Any ordinary three-column layout is not enough.
Suggested fix: Pick the most important thing and show it fully instead of equal boxes.
Several sections are decorated with leading 01, 02, 03 markers even though they do not describe real sequential steps. Actual numbered instructions are not this tell.
Suggested fix: Number only what really happens in order.
The visual design repeatedly nests rounded, bordered, or filled card surfaces inside other cards so multiple containers compete. A semantic wrapper or one nested example is not enough.
Suggested fix: One surface per region; group inside it with spacing.
A mosaic of unequal feature tiles is washed in separate accent tints and used to tease many features without showing a real workflow or product state. An informative dashboard grid is not this tell.
Suggested fix: Show the product doing one real thing instead of a mosaic of teasers.
A page combines a broad customer-logo wall with a rotating or templated testimonial carousel, but offers little specific customer context or result. A small number of named, concrete references is not this tell.
Suggested fix: Show one real customer with a real result, or nothing.
The page visibly retains a recognizable site-builder starter structure, placeholder copy, and stock sections with little product-specific editing. Detecting Webflow, Framer, or another builder in source code alone is not evidence.
Suggested fix: Replace the template's structure with one decided for your product.
A little context before you hit scan.
A higher score means your page matches more of the checklist’s familiar design and copy patterns. It is a second opinion, not a verdict on quality or proof that AI built your site.
0 · Fewer matches100 · More matches
60% comes from a whole-page estimate. The other 40% is a severity-weighted average of the eight strongest checks. The model evaluates screenshots, browser measurements, and visible copy. Individual check weights are this tool’s implementation of the public method.
Yes. Each report includes a copyable prompt with the strongest matches and their suggested fixes. Paste it into your assistant alongside your code, review its changes, and scan again.
Public HTTP and HTTPS pages. We look at the first three desktop screenfuls. Pages behind a login, private networks, interactive states, and motion are outside that capture.
Reports are shareable and visible to anyone with their link. Recent reports may appear on this page. Only scan public pages you are comfortable sharing.
It’s based on Made with Jev’s public AI Slop Detector, with design checks adapted from kill-ai-slop and copy checks from no-ai-slop. SlopFix is an independent implementation.
SlopFix is a free website design review tool by BAGS. It checks 34 visual and copy patterns, explains the matches, and turns them into an improvement prompt. It reviews your page; you choose and implement the changes.
A design pattern review complements usability testing, accessibility checks, and performance tools. The score does not prove who built a website or measure conversion.
Your next design decision starts with a closer look.