AI writing detector and humanizer
Find the patterns that make text read as machine-written — and rewrite them out without changing a single fact.
Your key stays in your browser.It goes straight to the provider, never to our servers, and we neither log nor keep it. Use a dedicated key with a spending cap, and delete it in the provider's dashboard when you are done.
Input
Result
The result will appear here.Readers have learned the tells: delve, tapestry, a testament to, in today's fast-paced world, the rule of three in every list, the closing paragraph that restates the opening, the em-dash in every sentence — and their Chinese cousins 赋能, 深入探讨, 不可或缺. The avoid-ai-writing skill catalogues these patterns with their exceptions, and this tool applies that catalogue two ways. Detect mode audits a text and lists each finding with the quoted words, why it reads as generated and a suggested fix. Rewrite mode removes the patterns while preserving every fact, number, name and quotation, in the author's voice or one you choose, and lists what changed.
How it works
- Findings are judged in context: a technical document repeats terms by design, a legal text hedges for a reason, and those are not flagged.
- The rewrite adds nothing — no facts, no experiences, no opinions — and where a vague word has no specific to replace it in the text, you get a bracketed placeholder instead of an invention.
- The audit is a writing-quality signal, not an authorship verdict: second-language writers and hurried humans produce the same shapes, and the tool says so.
Where your data goes
With your own key, what you type and the key go from your browser straight to the provider you choose; neither passes through Hysen Labs. In hosted mode, your text goes through our server to our provider (DeepSeek) and is billed in credits; we keep the token counts and cost of each run for billing, never the text itself or the answer. How the provider handles the text is governed by its own privacy policy.
This tool handles keys and credentials, so nothing about a run is saved, not even to your own history.
About your API key
We do not collect, store or leak your key: it lives only in this page's memory (unless you tick “remember in this tab”) and is gone when you close it. Still, treat any key you have pasted into a web page with care — create a dedicated key with a spending cap for use here, and delete or rotate it in your provider's dashboard when you are done.
What it costs
This tool is free, with no sign-in and no points.
Common questions
- Can this beat AI detectors?
- That is not what it is for, and detectors are unreliable enough that nobody should be using them for consequential decisions — published audits find false-positive rates above 60% on non-native English writers. What this tool does is make text better to read by removing the patterns that make readers stop trusting it.
- Does it work on Chinese text?
- Yes, with a pattern list for Chinese AI-isms — 赋能, 助力, 打造, 闭环, 抓手, 旨在, the 总而言之 closing paragraph — alongside the English one. The rewrite stays in the language of the original; the reply-language option only controls the language of the audit and the change list.
- Will it rewrite my code samples and quotes?
- No. Quotations, code blocks, URLs, tables and anything attributed to someone else are protected; a finding inside them is reported, not edited. The argument and structure of the text are kept unless you choose a voice that implies a change of register.
The open-source behind it
This tool's prompt is adapted from conorbronsdon/avoid-ai-writing (MIT) and runs on the model you choose. To use the same capability from the command line or inside your own program, start with that project.
conorbronsdon/avoid-ai-writingAlso known as
- humanize ai text
- remove ai writing patterns
- ai text detector free
- make ai writing sound human
- ai-isms checker
- delve tapestry testament ai words