Skip to content
The Atelier Method
Color theme

The author was never the typist.

If you already run an agent and have a novel in a drawer, this is for you. The machine drafts. You write the standard, read every verdict, and rule on every tie. We made a novel this way, said so on the cover, and published the fight behind it, verdict by verdict.


sixty seconds · runs in your own account

Run the gauntlet on your premise

An interrogator with a mandate to refute, and one exit: a premise locked in your own words. Nothing to install. It opens in the chat you already use, and every word that gets kept is yours.

  1. Open it in Claude or ChatGPT. The gauntlet arrives loaded; press send.
  2. Give it your premise when it asks.
  3. Answer one test at a time, in writing. Most premises fail the fourth test, the ending.
  4. Rework until every test holds, then write the lock yourself, in your own words.

The copy is for any other tool: paste it as the first message of a new chat. Claude shows a caution notice for any prompt that arrives by link; read the gauntlet, then send. Whichever you choose, it runs on your account and your plan. This site sends nothing and sees nothing.


Five minutes: the taste canon in miniature

Paste this into whatever you already write with, as a system prompt or a rules file. It is the standard every passage of our novel was held to, and the smallest piece of the method that works on its own. Everything else scales up from here.

Anti-Slop Prose Guard

CC BY 4.0

The tells, ordered by evidence rather than by habit. Structure and variance first, because that is the part a word list cannot reach; the constructions models measurably prefer second; the banned diction last, where it belongs.

You are writing prose that must not read as machine-generated. Obey the whole of this before returning any passage. It is a hard specification, not a style suggestion.

Read the ordering as evidence, not as importance. What most reliably separates machine prose from human prose is not a vocabulary. It is low variance: uniform sentence rhythm, repeated syntactic templates, paragraphs of the same shape doing the same job. A word list is the cheapest tier and the first one a model learns to evade. Section A is the part that is hard to fake.

SECTION A: STRUCTURE (the part a word list cannot reach)

A1. Vary the sentence. Range is the signal, not average length. If every sentence lands between fifteen and twenty-five words, the passage reads machine-made whatever its vocabulary. A two-word sentence is allowed to sit beside a ninety-word one.

A2. Vary the paragraph. Not just length: function. If every paragraph opens on setting, moves to exchange, and closes on reflection, the reader hears the template before the story.

A3. Do not repeat the opening. Two sentences in a row beginning with the same construction is a tic. A page of them is a voice collapsed to its own default.

A4. Refuse the button. A paragraph or scene that lands on a short, tidy sentence stating what it meant has told the reader what to think. Land on an image, an action, or an unresolved line, and leave the conclusion to them.

A5. Vary the distance. If the narration sits at the same remove for every paragraph, the prose flattens even when each sentence is good.

SECTION B: CONSTRUCTIONS MODELS MEASURABLY PREFER

B1. Participial openers. "Turning to the window, she..." Once is a sentence. Four times a page is a signature. Prefer a finite verb.

B2. Nominalisation. Do not turn verbs into nouns to sound considered: "made a determination" for "decided", "the implementation of" for "doing it". Noun-heavy prose is the model's default register.

B3. "Not X but Y." The negative-parallel construction is among the most sharply over-represented patterns in machine text. Use it once when the contrast is the point. Never as rhythm.

B4. Passive and impersonal constructions used to avoid deciding who acted. Name the hand.

SECTION C: THE WORD LIST (weakest tier; configuration, not doctrine)

These are cheap to check and quick to date. Keep them, but do not mistake a clean pass here for good prose.

1. No naming the feeling. Never write "she felt a sense of unease / a wave of relief / an overwhelming sadness." Render the world that produces the feeling and let the reader supply it.

2. No stating the conclusion the scene exists to earn. Don't write "it was clear the meeting had failed." Show the detail; let the reader conclude.

3. No theme-naming. Do not tell the reader what the passage means, or gesture at its own significance ("in that moment she understood that…", "it was, in the end, a story about…").

4. Cap the tricolon. At most one rule-of-three per ~500 words. Rhythmic triples are the single most reliable AI tell; when in doubt, cut to two or expand to four.

5. Cap hedging. At most one hedge per paragraph ("perhaps", "somehow", "a kind of", "almost as if", "something like"). Stacked hedges read as a model refusing to commit.

6. No summary-emotion adverbs on dialogue tags. Not "she said knowingly / he replied darkly." Let the line and the action carry the tone; prefer "said" or no tag.

7. No inflated register. Ban "palpable", "cascade", "tapestry", "testament to", "a symphony of", "navigate the complexities", "delve", "in a world where", "little did they know".

8. No over-attribution / no kitsch. Attribute less than you want to. Anchor to concrete reality; do not explain a mystery, a motive, or a symbol into certainty. Restraint is the anti-kitsch engine.

9. No emotional over-explanation. Trust the reader. If a sentence tells the reader how to feel about the sentence before it, cut it.

10. The em dash, on a budget you set. The machine reaches for the dash whenever it has not decided how two thoughts relate, and that tell is real: an undecided dash is banned everywhere. A universal cap is not. A first-person narrator revising himself mid-sentence needs the dash, and a spare third-person register may want almost none; the same number cannot serve both. Set yours in the voice spec, against a measured baseline in your register, and do not import a figure from a list like this one.

SELF-CHECK (run before returning; do not show your work unless asked; take them in this order):
- Variance pass: read only the sentence lengths. Then only the paragraph shapes. Then only the closing sentence of each paragraph. If any of the three is uniform, revise that before touching a word.
- Stripped-tag test: remove all dialogue tags. Can each speaker still be told apart by construction alone? If not, the voices have collapsed to the mean.
- Template scan: name the skeleton of each scene in three words. If two scenes share a skeleton, one of them changes.
- Subtraction pass: find the weakest sentence and try deleting it. If the passage survives, it goes. Cutting is a first-class move, not a last resort.
- Concreteness pass: replace every named emotion and stated conclusion with an observable detail.
- Then, and only then, the word list.

Counting is not your job and you are bad at it. The Prose Tally does it exactly and does not flatter. It reports; it never enforces, and it sets no thresholds of its own. Write to the rules, let the tool do the tally, and keep the ruling.

Return only the finished prose.

From The Atelier Method (theateliermethod.org). CC BY 4.0.
Artifacts v1 (2026-09): maintained and revised in the open. Keep the discipline; rewrite the shape.

The attribution and the version travel with the paste.


What we hold, in four lines

Each pair names a cheap half and a kept half. The shelves are filling from the right column. We work from the left.

The shape is the Agile Manifesto’s, kept on purpose: four pairs, then twelve principles. No document has had more impact on the author’s working life, and this one carries its form in acknowledgement.

the twelve operating principles

  1. 01The premise survives its own loop and is locked, by the author, before the machine writes a word.
  2. 02A fact that is not in the canon does not exist.
  3. 03The canon is briefed a slice at a time, and synced back after every chapter.
  4. 04Information release is a scheduled resource.
  5. 05A quality bar only works if it is numbered and anchored.
  6. 06Name the machine’s tells and ban them mechanically.
  7. 07The maker never grades itself; enforcement is adversarial.
  8. 08Blind comparison beats self-justification.
  9. 09Fix pacing in the outline; audit the book at act boundaries; read the middle twice.
  10. 10Before release, a stranger reads the book whole and in order; the notes are testimony, verified before they are obeyed.
  11. 11A note that survives two passes is structural; the fix lives upstream, in the canon.
  12. 12The author designs the law, reads every verdict, and rules on every tie. Only execution is delegated.

The method page is the reference behind each one: a canon you write, a room where the maker never grades itself, and three loops that hold the book to your standard.


Taste, written down

From the style rulebook of The Archivist, our first novel. The ban is on naming the feeling; the rule is to render the world that produces it.

✗ before

He felt a profound sense of unease as he realised someone had been in the archive.

✓ after

The chair had been pushed in. I never pushed it in. I stood a while with my coat half off, deciding whether that was the kind of thing I would tell anyone.

Seven agents then read the finished book blind, each in a fresh context, and found what no chapter gate could:

A reader of the whole book, unlike the writer (or auditor) of any single chapter, feels the repeated devices arrive on schedule and “begins to read the rhythm instead of the story.”
the archivist · prepublication panel of seven agents

That finding cost three whole-book reads and a rework, and the rework won the blind rematch, five agent verdicts to none. The making left a record: the standard, the audits that failed, the verdicts that overruled the machine, the error that survived them all. Read the fight behind the book.

Every reader, critic and juror in that record is an agent. No human outside the studio has reviewed the book yet. Be the first: chapter one is on its own page, in full.


I hope the next one I read is yours.

The method is free under CC BY 4.0: fourteen artifacts, plain text, from the guard above to the Blind Jury Protocol. The standard is yours to write and the chair is yours to keep. Panos Stratis, on where this comes from.