Get your own voice back.
Paste in a draft that reads like it came out of a prompt box, and NeverPrompted hands you back a version that sounds like you again, plus a plain comparison of what changed and why. It happens right here, in this browser tab, on this device.
Paste, drop a file, or upload .txt, .md, .rtf or .csv. Everything is read and processed on your device.
Your text is processed in this browser tab and never uploaded. Here is how that works.
- Runs on your device: open the network tab and watch nothing go out
- English, Spanish, French, German, Portuguese
- 20,000 free rewriting tokens every 7 days
Just a few of the brands that trust NeverPrompted
Ledgeur
Bill100
Brandmity
Chartely
Contextely
Contract10
Denial7
Duebay
Feedlark
Grannio
JobPlumb
Ledgerary
Lugbird
Patent77
Patientary
PermitBird
PortRobin
RenewBird
Rigbird
RotaBay
Scoutern
Sourceory
TableHelm
Underhaus
Vouchity
Hi Crafty
GradeHack
WillThisHappen
Frifti
Benefily
Classify7
Conformery
DeckHelm
Event70
Job13
Ledgerage
Ledgerler
Mealary
Meterary
ModelCharter
RoofHelm
Screen100
Slopeify
Spend7
WageCoachThree steps, and none of them touch a server.
The engine downloads to your browser once. Your draft is read and rewritten there, so there is nothing about your writing for anyone else to store, log or read.
Paste your draft in
Type it in, drop a file on the box, or use the upload button. Plain text, Markdown, RTF and CSV all read straight off your disk.
Press one button
Language and how much to change already have sensible defaults. They live under Advanced settings if you want to adjust them, and stay out of your way if you do not.
A workspace, not a wall of text
The button opens your workspace: the rewritten draft, a side-by-side comparison you can accept paragraph by paragraph, and the full check underneath if you want it. Everything you run stays on this device.
Not different words. Your words, read out loud.
You get a version that sounds like the person who actually wrote it: fewer stock phrases, less uniform rhythm, none of the tics a careful reader has learned to spot. You can compare every paragraph, before and after, and keep only the changes you agree with.
What changed, and why
Each paragraph shows its before and after side by side, so a change is something you can check, not something you have to take on trust.
Your call, paragraph by paragraph
Accept a rewrite, keep your own wording, or ask for another pass. Nothing is applied to the whole document without you seeing it first.
The technical check, for anyone who wants it
Underneath, the panel also reports whether a statistical watermark is present, plotted against a chance line with a confidence band around the figure. Most people never need this tab; it is there because we would rather show our working than ask for trust.
A mark was detected under one key.
NeverPrompted open reference scheme
not a vendor key
Green-list rate
68.0%
- Expected by chance
- 50.0%
- z
- 4.37
- p (one-sided)
- 0.000006
interval 60.1% to 75.0%
Measured over 147 distinct word pairs. Repeated pairs are counted once. The thin vertical line is the rate this statistic takes when no mark is present.
The chair thanked the working group for drafting the supporting brief, which those present found clear and remarkably short.
watermark z 2.36 · p 0.0092 · style distance not computed (passage too short to measure)
A question was registered about the budget line for the following stage, and the bursar committed to present exact totals to the following meeting rather than approximate them from recollection in the room.
watermark z 2.69 · p 0.0035 · style distance not computed (passage too short to measure)
What it does, and what it won’t pretend to do.
It shows its working
Every number on the panel is a real statistic, carrying the sample it came from and a range around it. Where something could not be measured, it says so rather than showing a zero and letting you assume it means something.
It won’t oversell you
No tool can promise a guaranteed result against every detector, so this one doesn’t try. It reduces detectable AI-style evidence, both the stylistic tells and, where the technique allows it, the statistical mark, and it always tells you what it tested.
Your writing stays yours
Rewriting runs on your device on every plan, with no hosted mode and no copy sent anywhere. It cannot guarantee beating an undisclosed watermark from a model vendor, because nobody outside that vendor holds the key, and it never says it can.
A style number, kept in perspective.
How far your prose sits from typical contemporary writing in the same language is a real, useful figure. It is also the easiest one to misread, so it is reported on its own and never folded into a verdict about how the text was produced.
Distance from a reference reflects register, subject and translation as much as anything else. Technical writing, fiction, translated text and non-native English all sit far from an encyclopaedic reference for entirely ordinary reasons, and none of that says anything about how a document was written.
0.64 SD
from contemporary reference prose
- Share of words used exactly once0.79 (+1.14 SD)
- Function words per 1,000 words493.83 (+1.13 SD)
- Commas per 1,000 words37.04 (-1.01 SD)
You can check this yourself.
If you would rather see it than take our word for it, the verify page lets you mark a passage under our published reference key in your own browser, then run the same passage against an unrelated key and watch the number sit at chance. It takes about fifteen seconds.
What that demonstration shows
- Marked text scored under the key it was marked with, clearly above chance.
- The same text scored under an unrelated key, sitting right back at chance.
NeverPrompted is for writing you wrote yourself.
Checking someone else’s writing, a student’s essay or a freelancer’s draft, is a different job with different ethics and a different tool. Learnaway is built for checking someone else’s work for AI use. This one is for your own words, not for judging somebody else’s.
Questions people actually ask
- Is a detected mark proof I used AI?
- No. A detected mark is not proof of authorship. Marks can appear in text that was quoted, translated, edited, or written with assistance, and a statistical test reports a probability rather than a fact about a person. NeverPrompted reports the strength of the signal and the passages carrying it, and states this limit on every result and every exported report.
- Can this tool guarantee my writing won't be flagged?
- No, and any tool that claims a 100% or guaranteed result is overselling a probabilistic process. NeverPrompted can reduce detectable AI-style evidence: both statistical watermark signal, where structurally possible, and human-perceptible AI tells like em dashes and stock phrasing. It cannot guarantee defeating a model vendor's undisclosed watermark, because nobody outside that vendor holds the key it was applied with, and no honest tool can promise otherwise. The rewrite runs entirely on your device, on every tier, and shows you the before/after evidence so you can judge the result yourself rather than take a guarantee on faith.
- Does NeverPrompted detect ChatGPT's or Claude's watermark specifically?
- Not unless this deployment holds that vendor's detection key, and no vendor currently publishes one; the result lists exactly which keys were tested, under "keysTested", so you can see that for yourself rather than take a claim on faith. NeverPrompted also reports a separate, key-free "AI-style likelihood" score: a heuristic that flags surface habits common in Claude, ChatGPT and other current model output (dash-clause connectors, stock phrasing, elevated vocabulary, uniform sentence length), deliberately biased to catch more real AI writing rather than to minimise false positives. It is not a statistical test and it is not a substitute for a real watermark result; see /guide/claude-ai-watermark for what a provenance mark actually is and why the key is the whole story.
- What's the difference between the Standard and Pro rewrite engines?
- Standard is deterministic substitution against the core AI-tell library: instant, no download, and included on every plan. Pro is a real language model that runs in your browser, generating more candidate rewrites per passage and using the extended AI-tell library; it comes with a Pro subscription rather than being metered on the free plan. What the free plan meters is how much rewriting you do: 20,000 tokens every 7 days, where a token is one word as this product counts them. Checking is never metered on either plan. Neither engine ever sends your text anywhere.
- Does my document ever leave my device?
- Not on the free check, and never on the rewrite feature, on any tier or surface. Checking runs in your browser: the detection engine is downloaded to your device and the text is measured there; you can confirm it by opening your browser network tab and watching while the check runs. The API, the MCP server and the PDF evidence report necessarily run on our servers for CHECKING, because a programmatic caller has no browser, and those paths are documented separately and are opt-in. Rewriting is different and stricter: it runs entirely on-device or in-process everywhere, in the browser, the API package, and the MCP server alike, with no hosted mode at all, on any tier.
- Which languages are supported at launch?
- English, Spanish, French, German and Portuguese. Each has its own reference baseline measured from real contemporary prose in that language; a language without a measured baseline is reported as unsupported rather than analysed against a substitute, because comparing Portuguese text to a Spanish reference produces deviations that look like findings and are artefacts.
- An absent mark: does that prove I wrote it myself?
- No, and this matters as much as the first answer. Marks survive editing poorly, are not applied by every system, and cannot be detected at all without the key used to apply them. No model vendor publishes its detection key. NeverPrompted tests the keys it holds and names them, so "no mark detected" always means "under these keys" and never "this document is clean".
- What can I actually hand to someone who has accused me?
- The Pro evidence report: a dated PDF carrying the signal strength with its confidence band, the per-passage breakdown after false-discovery-rate correction, the full stated limits, the list of keys tested, and a SHA-256 hash of the exact document analysed. The hash is what ties the report to one specific file, so the report cannot be waved at a different draft.
Write freely, then make it sound like you every time.
Pro gives you unlimited rewriting on your device with a stronger model and a wider library of AI tells to catch, so there is no weekly token budget to watch. If you also need a dated record of your own process, for a course requirement or a client, Pro adds a PDF report with the check results and a hash tying it to the exact file. That is a useful extra, not the reason to sign up.