# Humanised AI content · writing glossary · ScriptGrain > Humanised AI content is machine-drafted text revised so that its measurable habits (sentence rhythm, contractions, phrasing, punctuation) fall inside the range of human writing, as distinct from text rewritten only to fool a detector. The revision can be measured: before-and-after counts of the tells, and a voice-match score against a real writer. Canonical: https://scriptgrain.com/glossary/humanised-ai-content # Humanised AI content Humanised AI content is machine-drafted text revised so that its measurable habits (sentence rhythm, contractions, phrasing, punctuation) fall inside the range of human writing, as distinct from text rewritten only to fool a detector. The revision can be measured: before-and-after counts of the tells, and a voice-match score against a real writer. ## The numbers - Phrases and sentence shapes ScriptGrain's cliché checker counts as AI tells: **30 phrases, 10 shapes** ([ScriptGrain: AI-isms in marketing copy](https://scriptgrain.com/reference/ai-isms-in-marketing-copy)) - Median AI-tell density in 299 human pieces (per 1,000 words); 90th percentile 1.6: **0.4** ([ScriptGrain reference corpus](https://scriptgrain.com/reference/ai-isms-in-marketing-copy)) - Em dashes per draft from bare GPT-5 in SGR-002, against none from the profile arm: **17.5** ([SGR-002: ChatGPT vs a measured voice](https://scriptgrain.com/research/chatgpt-vs-a-measured-voice)) - Default voice-match target ScriptGrain's humaniser revises toward: **0.85** ([ScriptGrain: Humanize AI writing](https://scriptgrain.com/humanize-ai-writing)) ## What humanised AI content is The definition is narrow on purpose. It's not "AI content that sounds nice" or "AI content a person tidied up a bit". It's a specific process: scan for the known tells, count them, revise, rescan. The full list of what counts as a tell (30 phrases across four groups, plus ten detectable sentence shapes) lives at [/tools/ai-cliche-checker](https://scriptgrain.com/tools/ai-cliche-checker) and there's no point repeating it here. What matters for this glossary entry is the shape of the process, not the inventory. Humanising also isn't the same as writing to a brand voice from scratch. It's closer to editing: take a machine draft, strip the giveaways, and if you've got a measured voice profile, pull the prose towards that instead of towards a generic idea of "human". See [/glossary/voice-match](https://scriptgrain.com/glossary/voice-match) for what "pulled towards a voice" actually means in numbers. ## What changes when you measure it Here's the thing about humanising: you can't tell if it worked by eye. You have to count. The counts that move are the tells per 1,000 words, the em dash count, the short-sentence share, and the contraction rate. In SGR-001, running a banking brief through a voice profile took average sentence length from about 17 words to about 11, doubled the share of sentences under eight words (24% to 48%), lifted contractions by roughly 70%, and took ten em dashes down to none. One run, unedited, so treat it as directional. There's also a voice-match delta: how close the output sits to a target voice, measured, not guessed. In SGR-002, ScriptGrain's drafts scored 0.83 against a study profile and 0.91 against the held-out post itself. Bare GPT-5 scored 0.74 and 0.80. That gap is what "humanised" is supposed to close. ## Humanising versus evading a detector Here's the distinction, plainly: humanising fixes the writing. Evading fixes the score. Those aren't the same target, and chasing the second one is a trap, because detector scores don't reliably track voice quality. In SGR-002, the arm using GPT-5 with a one-page measured prompt scored highest on a detector's human score (0.78) while missing the target contraction rate by a mile: 0.5 per 1,000 words against a request for roughly 14, with judged formality at 7.2 against a target of 3.7. Meanwhile ScriptGrain's own drafts, which matched voice far better, scored lower on the detector (0.67). So beating a detector and sounding like a person are different problems, and detectors are unreliable in both directions: some human writing scores as machine-made, some machine writing scores as human. ScriptGrain reports detector scores because they're a data point. It doesn't sell evasion, and it won't ship a bypass feature. The humaniser revises towards natural variation, sentence-length spread, short sentences, contractions, removal of listed tells, and rescoring up to three passes towards a default of 0.85, reporting a miss honestly rather than rounding it up. ## What it cannot tell you Measuring tells and voice-match doesn't tell you whether the content is accurate, useful, or worth publishing. It tells you whether it reads like a person wrote it and, if you've supplied one, whether it reads like *you*. That's a narrower claim than it sounds. See [/humanize-ai-writing](https://scriptgrain.com/humanize-ai-writing) for the mechanics, and [/reference/ai-isms-in-marketing-copy](https://scriptgrain.com/reference/ai-isms-in-marketing-copy) for what these tells look like once they've escaped into actual marketing copy. ## Worked example a 300-word AI-written announcement paragraph, the usual suspects present: three "not X but Y" constructions doing the heavy lifting, tells running at roughly 6 per 1,000 words, not one sentence under eight words anywhere in the block, formal throughout with no contractions. after revision, the three "not X but Y" constructions are gone, replaced with plain statements. Tell density drops from 6 per 1,000 to under 1. Four sentences now sit under eight words, breaking up what was a wall of uniform 25-word sentences. Contractions appear where they'd naturally fall in speech. These numbers are illustrative, meant to show the kind of change humanising produces, not a guarantee for any given paragraph. the words carrying the actual announcement barely changed. What changed was the scaffolding around them, the rhythm, the hedges, the padding that told a reader (or a detector) that no one was actually talking to them. Fix that, and the content reads like someone wrote it because, by the end, someone did. ## Sources - [ScriptGrain: AI-isms in marketing copy](https://scriptgrain.com/reference/ai-isms-in-marketing-copy) - [ScriptGrain: the measurable markers of AI writing](https://scriptgrain.com/reference/markers-of-ai-writing) - [SGR-002: ChatGPT vs a measured voice](https://scriptgrain.com/research/chatgpt-vs-a-measured-voice) ## More terms - [Voice Match](https://scriptgrain.com/glossary/voice-match) - [Burstiness](https://scriptgrain.com/glossary/burstiness) - [Perplexity](https://scriptgrain.com/glossary/perplexity) - [Sentence Length Variance](https://scriptgrain.com/glossary/sentence-length-variance) - [Flesch Reading Ease](https://scriptgrain.com/glossary/flesch-reading-ease) - [Type-token ratio (TTR)](https://scriptgrain.com/glossary/type-token-ratio) - [Hapax legomenon](https://scriptgrain.com/glossary/hapax-legomenon) - [Function words](https://scriptgrain.com/glossary/function-words) - [Lexical density vs lexical diversity](https://scriptgrain.com/glossary/lexical-density-diversity) - [Stylometric fingerprint](https://scriptgrain.com/glossary/stylometric-fingerprint) - [Idiolect](https://scriptgrain.com/glossary/idiolect) - [Voice vs tone vs style](https://scriptgrain.com/glossary/voice-tone-style) - [Passive voice](https://scriptgrain.com/glossary/passive-voice) - [Tone matching](https://scriptgrain.com/glossary/tone-matching) - [Brand voice](https://scriptgrain.com/glossary/brand-voice) - [Voice drift](https://scriptgrain.com/glossary/voice-drift)