Writing Standards Every AI Should Follow (and the Tells That Give It Away)

Good writing has rules. AI breaks the same ones every time.

You know what I'm talking about. You read a paragraph and something's off before you can say what. The words are grammatical, the point is fine, but it reads like a robot doing an impression of a person.

It's the AI tells, of course. Sentence constructions like "here's the thing," or "it's not X, it's Y," or em dashes (sucks, I love em dashes) and words like "unleash."

Luckily, you can train AI to actually write like a human, all based on a set of standards that good writing follows, and a set of AI tells that break those standards.

That's how I constructed Flyletter. Each agent follows a set of universal writing standards that all writing output must adhere to.

And lucky for you, I'm here to tell you exactly how I built Flyletter's universal writing standards. Feel free to create your own, and then test it against Flyletter's output.

For a full breakdown on how to get AI to write like you, check out this guide on how Flyletter is engineered for voice.

1. The Quality Writing Floor

Good writing follows quality rules. Not vibes, not talent, not some gift you were born with. Learnable, specific rules that anyone can check.

They break into specific groups:

Sentence Craft

Vary your sentence length on purpose. Short sentences punch. Medium ones carry the explanation. Long ones build momentum, but only when they earn it.

Prefer active voice and present tense because they read with more authority. Cut gerunds when a plain verb does the job (write "start by mapping" not "starting by mapping"), and watch the fragment trap. A fragment can land hard for emphasis, but three fragments in a row is a model faking rhythm that real sentence variation should be doing.

Concision

Every word earns its place. If deleting a word doesn't change the meaning, delete it. Cut throat-clearing openers like "it's worth noting that." Cut hedging when you're not actually uncertain. Cut redundant pairs like "each and every."

Paragraph Discipline

One idea per paragraph. When you start a second point, start a new paragraph. A standalone one-sentence paragraph is powerful, so use it when a thought deserves the space. Vary your openers so two lines in a row don't start the same way.

Formatting Discipline

Every bold, every header, every list has to serve the content. A bold word should surprise the eye, not numb it. Decoration for its own sake is noise.

That's the floor. Every piece of writing, human or machine, should clear it before anyone reads it.

2. The Fact Standard

Before worrying about AI tells, one rule sits above all because breaking it costs more than a clunky sentence ever could.

A personal anecdote is a fact. It carries the same safety floor as a statistic.

A fabricated story destroys credibility the instant a reader recognizes it.

So the anti-fabrication rule has to be tight. Every anecdote has to trace back to one of three things: something the writer actually said or lived, a documented event or statistic you can verify, or a hypothetical the reader clearly recognizes as illustrative ("imagine a founder who..."). Anything else is invention.

This is the trust argument, and trust is what's at risk when you publish with AI-assisted writing. Everything else is style. Trust is the thing you can't rebuild once it's gone.

3. The Primary AI Tells

The AI tells aren't separate from the writing quality standards. They're what a broken standard looks like on the page. Start with the three loudest giveaways:

1. Stage-direction phrasing: The "here's the thing" move, where the writing announces it's about to make a point instead of just making it. A real writer makes the point.
2. The em dash at machine rate: People use em dashes. Machines use them constantly. The rate itself is the tell.
3. The colon as a dramatic pause: A colon before a standalone clause is throat-clearing dressed up as insight. Colons belong before lists and time references, not before a sentence that could stand on its own.

Underneath these giveaways are the pattern families, all of which are the same violations repeating in different costumes.

The contrast reveal ("this isn't X, it's Y") used as a reflex. The sweeping scene-setter that opens on "in today's world." The dramatic imperative opener barking "picture this." Filler transitions like "moreover" and synonym stacking, where three near-identical words pad a line one precise word would carry.

And then there are the categories of words that flag AI on sight. You know the ones. The hype verbs like "unleash," the consultant filler, the words no person uses in real life. I won't list them all here, partly because the list keeps growing, but mostly because once you're tuned to the standard you'll feel them yourself.

Each of these breaks a rule you already know. Stage directions break concision. The em dash and the colon break punctuation discipline. Synonym stacking breaks the one-precise-word standard.

Which ones do you notice the most?

4. The Human Test and the Real Fix

Spotting rule-breaking AI tells after a draft exists is whack-a-mole. You catch one em dash, three more show up next draft. You kill a stage direction, a synonym stack sneaks in behind it. You're fixing the same violations forever, one instance at a time, and you never actually get ahead.

There's a faster filter. Before any line ships, have the AI ask itself one question: would a busy, smart human write it this way? If the honest answer is "only an AI would write that," rewrite it. That single test catches most of the tells at once, because they all share the same root.

And that's the whole point. Good writing standards should be enforced holistically by the system, and not fall on you to call out.

Bottom Line

Test your last AI draft against this floor. Read it and count the tells, the stage directions, the em dashes, the borrowed intimacy. You'll find some. Everyone does.

Then ask why you had to go find them at all. At Flyletter, this floor isn't a setting you flip or a checklist you keep. It's the ground every agent already writes on, running before you read the first word.

Stop hunting for tells after the fact. Go set the right floor.