~ / insights / templates

Template · September 2026

AI-Tell Audit Sheet.

Six measurable patterns make prose read as machine-written. This sheet measures them before anything long gets published, and it ships with the script that does the counting.

Amit TiwariTemplate5 min read

The decision this protects

The gate, in order Run the script on the draft Fix every FIX until the script says PASS Read the hollow-reveal candidates by hand Portability test each; cut or keep with a reason Attach the verdict to the file and ship
Figure 1. The manual step is the hollow-reveal read. Everything else is a script.

Whether a piece of long prose ships. Not whether it was written with machine assistance, which is unknowable from the text and not the point, but whether it reads like it was, because the fingerprint costs credibility with exactly the readers worth having. The audit turns “does this feel AI-written” from an argument into six numbers and a candidate list.

Before you start

  • The finished draft, in HTML or Markdown, prose complete.
  • The audit script published with this sheet, run as python3 ai_tell_audit.py draft.md.
  • Ten minutes for the manual half, reading the hollow-reveal candidates the script surfaces.

Stated limits

  • The audit measures style, not truth. A piece can pass every threshold and still contain a wrong figure; fact-checking is a separate gate.
  • The thresholds are tuned on this site’s own published pieces, and they are opinions with numbers attached, so recalibrate them against prose you consider clean rather than treating them as laws.
  • A pass is necessary, never sufficient. The audit cannot detect a piece that says nothing; it can only confirm the nothing is well punctuated.

1. The lexicon count

The thresholds, as the script applies them Overused lexicon, hits per 1,000 0.5 Em dashes per 1,000 (site rule: 0) 3 Colon-then-explanation per 1,000 4 Short fragments, share of sentences (%) 10 Long sentences (36+), per 1,000, minimum 2 Green bars are ceilings; the blue bar is a floor. The three named constructions have a threshold of zero and are not drawn.
Figure 2. Six numbers. Opinions with thresholds attached, tuned on this site’s own pieces.
Field What to record Why it matters
Hits per 1,000 words From the script’s word list (delve, tapestry, realm, pivotal, seamless, harness, journey and the rest) These words cluster in machine prose at rates human editors do not tolerate
The hits themselves Each word and its count One hit is a word choice; five are a fingerprint
Threshold 0.5 per 1,000 or lower A 7,000-word piece earns three misses at most

Judgment prompt: For each hit, is there a plainer word that says the same thing, and if not, why not?

2. Dash density

Field What to record Why it matters
Em dashes per 1,000 words Count of em dashes and en dashes doing em-dash work Edited human prose runs one to three per 1,000; machine drafts run several times that
Threshold 3 per 1,000; this site’s own rule is zero The dash is the single loudest tell, which is why the house style bans it outright

Judgment prompt: Does each dash survive being replaced by a comma, a full stop or nothing?

3. Hollow reveals

Field What to record Why it matters
Candidates Short fragment followed by an abstraction, X. That is the opportunity. and its family The confident-staccato resolution that asserts significance instead of supplying it
Portability test result per candidate Could the line be pasted into a piece on an unrelated subject If yes, it says nothing specific and gets cut
Threshold Zero surviving candidates Each one is replaced with a figure, a date, a named thing or a concrete consequence

Judgment prompt: What specific fact was the cut line gesturing at, and can that fact take its place?

4. Colon explanations

Field What to record Why it matters
“Clause: lowercase explanation” per 1,000 words From the script The strongest residual pattern in machine prose after the obvious tells are cleaned
Threshold 4 per 1,000 or lower Two sentences usually carry the same content without the tic

Judgment prompt: Read three of them aloud; does the rhythm repeat?

5. Fragment share and the long tail

Field What to record Why it matters
Share of sentences with 5 words or fewer From the script Fine alone; combined with the patterns above it produces the staccato tell
Sentences of 36 or more words per 1,000 From the script A real long tail is a strong human signal; models regress to the mean sentence
Thresholds Fragments under 10 percent; long tail at 2 per 1,000 or more Both are distribution checks, not bans

Judgment prompt: Do the long sentences actually need their length, or are they three sentences holding hands?

6. The named constructions

Field What to record Why it matters
not just X but Y count From the script A reflex construction that inflates without adding
That is not X. That is Y. count From the script The same reflex with a full stop in it
In today's openers From the script The classic throat-clear
Threshold Zero, zero, zero Each has a plainer sentence inside it

Judgment prompt: None needed; these are mechanical cuts.

The defensible output

Interactive: paste a draft and run the six measures in your browser. Needs JavaScript.

What the audit found on a real piece before and after the edit MEASURE A MACHINE DRAFT, 7,000 WORDS AFTER EDITING THRESHOLD Em dashes per 1,000 10.6 0 3 (site: 0) Overused lexicon per 1,000 0.3 0.3 0.5 Colon explanations per 1,000 5.9 3.1 4 Short fragments 9.1% 6.4% 10% Long sentences per 1,000 4.2 4.2 2 minimum Hollow reveals surviving 3 0 0 [VERIFY: the before column is a 7,067-word piece edited in August 2026; the after column is a placeholder. Replace both from the audit log.]
Figure 3. The dash count is the loudest tell and the easiest fix. The colon habit is the one that survives the first edit.

The script’s one-line verdict per measure, PASS or FIX, attached to the piece’s file, plus the hollow-reveal candidates with a one-word disposition each, cut or kept-because. A piece ships when every measure reads PASS and every kept candidate has its reason written down. The record means that when someone calls a published piece machine-flavoured, the answer is the audit sheet, not a shrug.

Where I could be wrong

The fingerprint moves. These six measures describe machine prose as it reads now, and the lexicon in particular decays; words drop out of fashion in the models and new ones arrive. The sheet is dated and the word list needs re-tuning on that schedule, roughly yearly.

There is also a ceiling to what style measurement buys. Prose that passes can still be hollow in ways no counter catches, and human writing that is merely bad fails several thresholds while being entirely human. The audit reduces false positives for machine flavour; it does not grade writing.

Sources

How to cite this template

Amit Tiwari (2026). AI-Tell Audit Sheet. Template, September 2026. amittiwari.net. https://amittiwari.net/templates/ai-tell-audit-sheet

Send me the template

A filled example alongside the blank one, so you can see how it is meant to be used.

So I can look before we talk.

Discuss in the community ↗