Evally
Start free
Content & growth

AI slop detector

Stamp generic, filler-stuffed, template-shaped AI writing, with the tells quoted.

Checks text for the tells of low-effort AI writing: nothing specific, filler phrases, the hook-and-lessons template, buzzwords, the 'it's not X, it's Y' tic, and no first-hand insight. Use it on your own drafts before you post, or to filter a feed.

Use this judgeCustomize it

Try it live

Real calls to Jev. Pick an example or paste your own.

Examples
236
No verdict yet

Pick an example or paste your own input, then run it.

Under the hood

Every question and rule, in the open. Fork it to change any of them.

What it asks

Reads text, then asks 7 questions in one call.

  1. Q1Says nothing specificYes / no

    Could the text be posted by thousands of people unchanged, because it contains no concrete example, number, name or first-hand detail?

  2. Q2Filler phrasesYes / no quotes evidence

    Is the text padded with filler phrases such as 'in today's fast-paced world', 'it's important to note', 'let's dive in', 'game-changer' or 'unlock your potential'?

  3. Q3Template-shapedYes / no

    Does the text follow an obvious template: one-line paragraphs, a hook, a list of 'lessons', and a closing question asking for comments?

  4. Q4BuzzwordsYes / no quotes evidence

    Is the text stuffed with buzzwords (leverage, synergy, delve, tapestry, robust, seamless, transformative)?

  5. Q5'It's not X, it's Y'Yes / no quotes evidence

    Does the text lean on 'It's not X, it's Y' or 'X isn't just Y, it's Z' constructions?

  6. Q6First-hand insightYes / no

    Does the text include an experience or an insight the writer clearly had themselves?

  7. Q7Value to a readerScore

    How much would a reader learn from the text?

    1. 0Nothing
    2. 1A little
    3. 2Something useful
    4. 3A lot

How it decides

Rules run in code, top to bottom. The first one that matches gives the verdict.

  1. 1
    If Slop score ≥ 60AI slop
  2. 2
    If Slop score ≥ 38Some slop
  3. ·
    DefaultHuman & useful
Slop score

A 0-100 score weighted from Says nothing specific ×2, Filler phrases ×1, Template-shaped ×1, Buzzwords ×1, 'It's not X, it's Y' ×1, First-hand insight (inverted) ×1.5, Value to a reader (inverted) ×1.5.

Call it from your code

Every template runs as-is with an API key, no setup: POST /api/v1/judges/ai-slop-detector/run.

curl -X POST https://tryevally.com/api/v1/judges/ai-slop-detector/run \  -H "Authorization: Bearer $EVALLY_API_KEY" \  -H "Content-Type: application/json" \  -d '{  "input": {    "text": "In today'\''s fast-paced world, leadership isn'\''t just a title. It'\''s a mindset.\n\nHere are 5 lessons I learned:\n1. Communication is key.\n2. Embrace change.\n3. Leverage synergy.\n4. Never stop learning.\n5. Be authentic.\n\nWhat would you add? 👇"  }}'

Seen in the wild

Community builds on Jev that use this pattern. Not affiliated with Evally.

More in Content & growth