0
/ 100
Style signal index
Low signal
A style score, not an AI probability.
Jev Free to use · no login
Free AI slop detector.
See every tell.
Paste your text once. Jev checks every sentence against recognizable AI-writing patterns, then shows exactly what deserves a second look.
01
Paste your text
02
One fast pass
From raw text to a reviewable signal map.
- 1 Analyze with JevScore the writing signals
- 2 Show detectionsHighlight only the flagged sentences
No login. Don’t paste confidential data. Text is processed by this site and TypeSafe; see TypeSafe privacy.
Scanning is temporarily unavailable.
The service operator needs to finish configuring Jev. Please try again later.
03
Review the signals
Jev analyzed the passage sentence by sentence.
Highlighted
0 of 0 sentencesMost common signal
None No repeated pattern found.
Read this as a writing aid, not a verdict.
AI-style patterns also occur in human prose. Wikipedia explicitly warns that these signs and automated detectors can produce false positives.
Read the source rubric ↗FAQ How it works
What happens
when you scan?
A transparent look at what Jev checks, what gets highlighted, and what the result can—and cannot—tell you.
How does Jev Detector analyze my text?
The server preserves each sentence’s exact position, sends bounded batches to TypeSafe’s Jev model, and asks for both a 0–4 style score and the strongest matching signal from a Wikipedia-derived rubric. The stopwatch covers the full request-to-render time.
What appears in the review?
Only sentences that cross the detector’s evidence threshold. Use the arrows to move through detections and see the original sentence number, signal category, Jev score, confidence, and matched wording.
Does a highlight prove the text was written by AI?
No. It marks a recognizable writing pattern, not authorship. Human prose can contain the same patterns, so every result needs human judgment and should never be the sole basis for a high-stakes decision.
If I remove this, will my text become undetectable?
No. AI detectors look at more than common, obvious tells, and removing a few highlighted phrases cannot guarantee an undetectable result. For a complete rewrite designed to reduce detection signals, visit Make your content undetectable with StealthGPT ↗
Can I edit after scanning?
Yes. Click anywhere on the scanned text—or choose “Edit in place”—to return to the same editor at the clicked position. Your text is kept; you never need to clear it first.
How much text can I scan?
Up to 10,000 words at once, with no sentence-count rule. Extremely sentence-dense documents are grouped into adjacent passages so the scan remains reliable and bounded.
Is my pasted text stored?
This app has no accounts or document database and does not save pasted text in application code. Text is processed by Vercel and TypeSafe to provide the scan, so confidential material should not be submitted. See the privacy page for details.