Anyone can generate text. I answer for every claim.
Why AI-drafted copy needs more than a proofread
In a Gartner survey of 1,006 US consumers, 57% said AI-generated content had made them less trusting of brand messaging. Another promise about quality won’t answer that. I check machine-drafted copy against its sources before it goes out, and I’ve put the checks on this page for you to repeat. You can judge the work for yourself.
The figures and their sources
The premise: most new web pages now carry AI-written text
Ahrefs ran its own detector over 900,000 pages its crawler first found in April 2025, one page from each site. About three in four contained AI-generated text, and most of those mixed it with human writing. The figures are one detector’s estimates, not proof of who wrote any given page.
900,000 new pages, by how much of the text was AI-generated
Readers distrust it, and cannot reliably spot it
The first grid is Gartner’s release of 22 September 2026, a survey of 1,006 US consumers. Bynder’s 2024 survey of 2,000 UK and US consumers put two articles side by side, one written by an LLM and one by a trained copywriter (the second and third grids). The fourth is Gartner’s release of 16 March 2026. Each grid is 100 people, scaled from the survey percentages.
It says what is not so
About 1 in 4
Answers the median model invented to questions about things a document never mentions, at a 32K context
A 2026 preprint tested 35 open-weight models with questions the source cannot answer. The best invented an answer 1.19% of the time at 32K, and 10.25% at 200K. The longer the source, the more closely a draft needs checking.
It gets accused, and the detectors disagree
AI detectors disagree: the Authors Guild ran five detectors on ten human-written articles from 2022 or earlier. One detector’s score is weak evidence on its own.
It may need a label
Since 2 Aug 2026
The EU AI Act requires a clear label on AI-generated text published to inform the public on matters of public interest, unless it has undergone human review or editorial control and a person or company holds editorial responsibility for the publication. Scope is a question for legal advisers.
Published work
Four retained accounts, with clients in the UK, the US, and Malta. The professional-range copy written by hand at BRITA is still live.
UK English master content for the professional water-filtration range, translated for eleven international subsidiaries.
Researched and written without AI
Public-sector content for procurement officers and specifiers, who read for compliance before they read for interest.
A US SaaS case study, written to carry the client’s story without the usual superlatives.
A project story for procurement officers and specifiers: planters and reclaimed timber seating for a courtyard in Didcot.
A sector page for fine-dining kitchens: water filtration for steam cooking, espresso, and glass washing.
Researched and written without AI
Writing across audiences
One method, three kinds of reader. Each sample is a complete piece for a real brand, written in that brand’s own voice. The language changes with the audience; the editorial standard does not. Figures are traced to their sources, and the accompanying notes show how claims were checked, corrected, or held back.
Independent, speculative portfolio concepts. None was commissioned by, or is affiliated with, the brands featured.
Two entries from its ledger
- Flagged “FAQ quotes a price no card carries”
The price cards agree in all 24 markets. The FAQ answer contradicts its card in 10 of the 22 that quote one.
- Corrected “every fact right and the voice wrong”
The previous draft used no contractions. Remote’s own pages were measured first, and the copy follows them.
Two entries from its ledger
- Verified “Which prices the RB880 at twenty-five pounds”
£2,000 complete, less £1,280 for a standard Planar 6 and £695 for the Nd9, as The Ear reported in April 2026. The review itself puts the arm at £25 in the package.
- Held back “Not published. Still.”
Rega publishes no wow and flutter or rumble figures, so none is borrowed.
Two entries from its ledger
- Corrected “Maltese makes up 0.0032%”
neuromaltese.mt gives 0.03%. The crawl itself publishes 0.0032%, so the page uses the published figure.
- Counted “Ten projects for the Maltese public sector since 2024”
The count of published government case studies. The true number may be higher.
The worked example
Test three below is built from this page’s ledger, and Lexiphon quotes it as a brief.
Two entries from its ledger
- Held back “The gearbox is an Xtrac six-speed”
The gearbox is named without its mass. The gearbox mass, an unsourced number, was held back on veracity grounds.
- Verified “Every figure traced to the Gordon Murray Automotive T.33 Spider technical specification and launch release”
The figures. Except one: what the V12 sounds like at 11,100 was never written into the specification.
Test three How it checks
Find the error
Checking means finding the claim that does not hold, so here is a paragraph with three of them.
The paragraph is about the Gordon Murray Automotive T.33 Spider and uses only claims named in the evidence ledger on its concept page; three were held back or corrected there. Mark the phrases you doubt, then press Check to see how many errors you found and how many false alarms you raised. Each answer links to its pin in the evidence viewer.
This paragraph contains three deliberate errors.
Gordon Murray Automotive took the T.33 Spider’s brief to Cosworth, and the result is a bespoke V12 with gear-driven ancillaries, built in the spirit of 1960s V12 engines. The Cosworth GMA.2 revs to 12,100 revolutions per minute. The structure is a carbon laminate, and the laminate is isotropic. The downforce is made underneath. It comes from shear at the front splitter.
Each of the three was held back or corrected on the T.33 Spider concept page. See them in place, beside their notes.
The three answers
- revs to 12,100 revolutions per minute. The 12,100 rpm record belongs to the T.50 and was kept off the T.33, whose Cosworth GMA.2 V12 is limited to 11,100.
- is isotropic. “Isotropic” was held back for a carbon laminate, which is anisotropic by design, so “torsional” was used instead.
- shear at the front splitter. “Shear” at a front splitter was held back on veracity grounds: the car does not have one.
The full record
Eight entries from the ledgers sit on the cards, two on each. The four documents carry 37 in all.
How I work with machine-drafted copy
The work begins by checking each claim against its source, then revising the language without losing the facts. The decisions are recorded so you can see what changed and why.
The five-step method begins with your source material. A model drafts from it; I check the claims, revise the language, and verify the evidence again before you sign off. Below, a deposit claim from the Remote sample shows how an omission is caught, corrected, and documented. Three tests and two tools let you examine the method for yourself.
How a piece reaches you
Five steps, taken in order, with a written record at the end.
The example follows the deposit claim in the Remote sample’s ledger, H5 against F08. The draft line is illustrative, written for this page.
You send the source
Specifications, standards, product sheets, contract small print: whatever your claims rest on.
Source: the startup line says no deposit, and the FAQ says a reserve may apply.
A model drafts
It drafts from that material, in your voice, and the draft counts as unchecked until step three.
Draft: no deposit or setup fees.
I check every claim
Each one goes back to its source. What I cannot source is flagged, corrected, or held back, and never invented.
Flagged: the reserve has gone from the draft.
I read it for tells
I rewrite machine phrasing and flat rhythm, and then every claim gets its second check.
Checked again: no standard deposit; a refundable reserve may apply.
You get the record
The finished piece arrives with its production notes: what was checked, what was held back, and why. You sign it off.
Recorded: the startup line held back (H5).
Check a signed-off text
Every piece I deliver carries a fingerprint in its production record, so you can check later that the text you hold is the same version I signed off.
Paste a text I delivered and the fingerprint from its production record. Your browser does the computing, and nothing leaves it.
This text’s fingerprint:
A match proves the text is unchanged. It says nothing about who wrote it.
I used LLMs to build a resource that demonstrates why human editorial judgement remains essential to good writing. The distinction lies between generating plausible language and deciding what deserves to stand, a decision that requires direction, verification, and accountability.
System risk
One claim. Eight outputs.
On 16 October 2026, Remote’s pricing page offered startups no deposit or setup fees. Its FAQ, however, said a refundable reserve may apply. Miss that qualification, and the unqualified promise finds its way into an article, a sales leave-behind, a lifecycle email, an answer block, an FAQ, a campaign line, a transcreation, and an image-to-video brief. Eight pieces of copy, all carrying the same omission.
Unchecked
- Claim
- No deposit or setup fees (startup offer)
- Source status
- The pricing FAQ on the same page says a refundable reserve may apply.
- Label
- Held back
- Editorial note
- Needs a source before any surface repeats it.
I Article
Remote charges no deposit and no setup fees. The first invoice is the first money you move.
Carries the unchecked claim
II Sales leave-behind
No deposit. No setup fees. Start today.
Carries the unchecked claim
III Lifecycle email
Good news before your first invoice: Remote takes no deposit, so there’s nothing to pay up front.
Carries the unchecked claim
IV Answer block
Does Remote charge a deposit for Employer of Record? No. Remote does not charge a deposit.
Carries the unchecked claim
V FAQ
Do I pay a deposit? No. There is no deposit, and no setup fees.
Carries the unchecked claim
VI Campaign line
No deposit. No delay.
Carries the unchecked claim
VII Transcreation
No deposit to pay, and nothing to arrange first.
Carries the unchecked claim
VIII Image-to-video brief
On-screen text, final frame: NO DEPOSIT. NO SETUP FEES.
Carries the unchecked claim
Compare the lines with the record above. “Nothing to pay up front” appears in the email and “no delay” in the campaign line, and neither source line says either. The sixteen lines on this page are drafted for it and are not Remote’s copy.
Where it goes
One unsupported promise, copied eight times, is eight places to correct. Each line reads well, and none names its source.
Verified
- Claim
- No standard deposit; a refundable reserve may apply, confirmed during onboarding and disclosed before payment; unused balance credited or refunded
- Source status
- Remote’s en-GB pricing FAQ, read 16 October 2026 (ledger F08).
- Label
- Verified
- Editorial note
- Use this wording. Keep the reserve with the promise.
I Article
Remote charges no standard deposit. If a refundable reserve applies, Remote confirms the amount during onboarding and tells you before you pay.
Carries the verified record
II Sales leave-behind
No standard deposit and no setup fees. Any reserve is refundable and shown before you pay.
Carries the verified record
III Lifecycle email
A note on money before your first invoice: Remote takes no standard deposit. If a reserve applies, we’ll confirm the amount with you during onboarding, before you pay.
Carries the verified record
IV Answer block
Remote doesn’t charge a standard deposit for Employer of Record. In certain circumstances Remote may require a refundable reserve to cover employment-related obligations.
Carries the verified record
V FAQ
Do I pay a deposit? Not a standard one. A refundable reserve may apply, and Remote tells you the amount before you pay.
Carries the verified record
VI Campaign line
No standard deposit. Any reserve is refundable.
Carries the verified record
VII Transcreation
No standard deposit to pay. Where a reserve applies, it is refundable and confirmed before you pay.
Carries the verified record
VIII Image-to-video brief
On-screen text, final frame: NO STANDARD DEPOSIT. A small line beneath: any reserve is refundable.
Carries the verified record
Every line keeps the reserve beside the promise. The sixteen lines on this page are drafted for it and are not Remote’s copy. See the Remote sample.
What changes
One checked record gives all eight surfaces the same words. Each still needs an editor, and none can promise more than the source does.
Test two How it reads
How a sentence lands
Why some sentences stick and others slide past, measured as you read.
English saves its heaviest information for the end of a sentence; grammarians call it end focus. Whatever sits in the final seat is what the reader keeps, so I give that seat to the fact, and cut any clause that would steal it. In the large headings on this page, the weight builds towards the words where each sentence lands.
Across a paragraph, sentences hold a reader when their lengths vary, long against short. Two numbers measure it: spread, how far the lengths vary, and clumping, whether similar lengths travel together or alternate.
Both are composition standards. No score here, or anywhere else, settles who or what wrote a text.
Sources
End focus: Quirk, Greenbaum, Leech, and Svartvik, A Comprehensive Grammar of the English Language (1985). The structural check simplifies Joachim Lambek, “The Mathematics of Sentence Structure”, The American Mathematical Monthly 65(3), 1958, pp. 154–170.
Rhythm reference: Abraham Lincoln, Second Inaugural Address, 4 March 1865, from the Avalon Project at Yale Law School. Sentence splitting is heuristic.
Wide spread, and long and short alternate. Short sentences, eight words or fewer, show in red. For reference, Lincoln reads 0.74 and 0.18.
In detail: how grammar decides the last word
Lambek gives every word a type. A name is n and a sentence is s. An intransitive verb such as works is n\s: it takes a name on its left and returns a sentence. Two rules do the cancelling. A type x/y followed by y gives x; a y followed by y\x gives x.
Final: the payload cancels last
Draft: the tail cancels after the sentence is complete
The final seat belongs to whatever cancels last on the right. In the draft, the sentence was already complete at “ring”, so the trailing clause cancels against a finished s and takes the beat. Lambek called his own assignment of types “tentative”, and these are a working simplification in the same spirit. He withholds n from pronouns, so the n on “It” is ours.
In detail: how the two rhythm scores are calculated
For sentence lengths x₁ … xₙ with mean μ and population standard deviation σ:
Clumping is the lag-1 autocorrelation. Negative values mean long sentences tend to follow short ones, and positive values mean similar lengths travel in packs.
Test one How it reads
One pitch, written two ways
Copy with one rhythm and the same stock phrases sounds like every competitor’s page, and a buyer has little reason to keep reading.
Each struck-through phrase is a tell, counted live.
Each word plays as one note, longer words hold longer, each sentence ends on a held note, and every tell plays flat.
How it plays
- A bar is one word. A longer word lasts longer, and a comma or a full stop adds a rest.
- Height is pitch: it rises towards the middle of a sentence and falls back, nudged by the length of each word.
- A tall bar with a dot is the end of a sentence, held on the home note.
- A bar with a flat cap is a tell, played out of tune and falling.
- A low note holds under each sentence, and the pale band shows how long it lasts.
- Both texts play under the same rules on one time line, and the same text always plays the same way.
Before: a typical AI-style pitch, written by me as a sample
4 tells, 40 words
I’m a results-driven content strategist with a passion for crafting compelling narratives that resonate with target audiences. With a proven track record across diverse industries, I leverage data-driven insights to deliver impactful content that drives engagement and elevates brand visibility.
Written for anyone. Four tells from the house list, two long sentences in a row, and not one claim a reader could check. The list counts machine vocabulary, not every CV cliché: “proven track record” passes the scanner and still fails the reader.
After: checked, for marketing leaders
0 tells, 42 words
Drafts now arrive faster than anyone can check them. Each one ships under your name. I rewrite machine-drafted copy against your house standards: every claim traces to a source, every market hears one brand. Four retained accounts are held to that standard.
Written for marketing leaders. It opens on their problem, and two short lines land the point before the detail.
Why each line changed
Drafts now arrive faster than anyone can check them. Each one ships under your name.
Register Opens on the problem the reader owns, in the reader’s terms. Rhythm A short line after a longer one.I rewrite machine-drafted copy against your house standards.
Claim Names the service and the yardstick where the Before names a trait.every claim traces to a source, every market hears one brand.
Claim Two checkable promises replace “proven track record”.Four retained accounts are held to that standard.
Claim A count the reader can query replaces “diverse industries”.
Now try your own copy.
What does your company sound like?
A company can explain what it does, what it believes, and why it exists. But how does it sound when it speaks? Its voice is part of its identity, and its tone changes with the audience and occasion. I designed Lexiphon to put that voice on the page, where you can see it, test it, and change it. Bring a paragraph you are proud of, or one you suspect sounds like everyone else’s.
Studio A tone-of-voice tool
Lexiphon
Lexiphon is a browser-based tool for exploring tone of voice. Choose a voice, watch the same facts take on different characters, and check a draft against the rules behind it. It runs in your browser and calls no language model, and nothing you type is sent anywhere.
Adjust the voice
How to read it
The four tone dimensions are the Nielsen Norman Group’s (2016). The twelve archetypes come from Margaret Mark and Carol S. Pearson, The Hero and the Outlaw (2001); where each sits on the four dials is my reading, and so is every rule that turns tone into structure. Two briefs are invented, as each one says. The other two quote real pages: the concept page for the Gordon Murray Automotive T.33 Spider, and this site. Checking a draft, Lexiphon can measure formality and enthusiasm by proxy, sentence lengths, point of view, and figures that need a source. It cannot measure humour or respect, or tell whether a claim is true.
Telltale
Telltale is a browser tool that marks every phrase from my house list of machine-sounding copy in text you paste, in three groups: rewrite on sight, needs a reason, and structural pattern.
Some words turn up in machine-written text far more often than in human writing, and people who use chat models have learnt to spot them.
The test runs my own house list, which is growing: 135 words and phrases to rewrite on sight, 68 that need a reason, and 14 structural patterns. It began with the words named in published research and in the guide Wikipedia’s editors keep on signs of AI writing.
A hit is a register problem. It is never proof of authorship: several of these words were already rising in academic prose before chat models arrived. Structure beyond these patterns still needs a human reader.
Sources
Kobak, González-Márquez, Horvát, and Lause, “Delving into LLM-assisted writing in biomedical publications through excess vocabulary”, Science Advances 11, eadt3813 (2025).
Russell, Karpinska, and Iyyer, “People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text”, ACL 2025.
Matsui, “Delving Into PubMed Records”, Perspectives on Medical Education 14(1), 2025.
Wikipedia, “Signs of AI writing”, consulted 23 September 2026.
Open Telltale
Test any text with Telltale
Paste a bio, a job advert, or a draft of your own. The test marks every tell it recognises as you type, and nothing you enter leaves your browser.
Rewrite on sight Needs a reason Structural pattern Hover over a mark to see its entry.
The last reader before release
Where this judgement belongs inside an AI company
Upstream
Source and knowledge integrity
Identify authoritative information, conflicting claims, knowledge gaps, and source limitations before content is drafted.
Production
Model-output evaluation
Work with content, product, and technical teams to establish review criteria, identify recurring failure patterns, and improve human and AI workflows.
Downstream
Publication accountability
Keep a record of editorial interventions, manage tone across channels, and clarify what requires expert or legal sign-off.
Who is behind the checks
Checking sources came before writing in my training, and it still comes first in my work.
Someone has to be sure that every sentence is true before it goes out, and I like being that person, the last reader before the buyer. The work lives in specifications, standards, and contract small print, the dense documents that regulated industries run on, line after line. Every line reaches a buyer. That buyer reads the English and believes it, so every figure is checked against its clause before it reaches them. Every decimal against the standard that set it. Every sentence against the page. Nothing goes out on faith, and what goes out is English a buyer can trust.
What it takes to stand behind a claim
Checking copy means more than matching a sentence to its source. A claim may be technically accurate yet omit the condition that changes its meaning. Three kinds of work have taught me to recognise where that happens.
Keep every claim within the evidence
At BRITA, I wrote the master content for a water-filtration range in an industry governed by technical standards. Product specifications established what could be claimed, not what sounded persuasive. I learnt to recognise the point at which a supported fact becomes an unsupported promise.
Preserve meaning through revision
At CM-AG, I drafted the company’s first and only patent application, subsequently published in the US.
In separate work for a German law firm, I translated extensive materials from international fraud cases into English for New York attorneys, with individual translations exceeding 20,000 words.
Both demanded close attention to detail and precise transcription. In a patent, a qualification can define the scope of a claim; in a legal case, a single word can distinguish an allegation from an established fact. I apply the same discipline when checking and revising machine-drafted copy.
Make every editorial judgement defensible
At micro1, my annotations undergo peer review, and I review those of my colleagues. Each judgement must be supported by the criteria, not simply by my confidence in it. The same principle governs my editorial checks: I need to be able to show why a claim stands, why it needs correcting, or why it should not appear at all.
The record: experience, published work, clients, and sectors
The page shows the method.
The work carries my name.
If you are hiring, send me the role, and I will answer with the work that fits it best.
One email is enough, and I reply within one working day.