Get in touch

Master library

AI copywriting tell library

An exhaustive taxonomy of the words, phrases, structures and habits that make copy feel generated — organised so you can score them systematically.

~250 tells · 18 diagnostic categories

AI-associated does not mean forbidden.

AI uses ordinary English. Trying to purge every word it favours would make the writing worse. The point of this library is to spot overuse, predictability, genericity and lack of intention — then give the writer better choices.

Humans write these tells too. The diagnosis is about autopilot writing, not machine authorship.

It might not always be AI

When a “tell” isn’t a tell — and what to look for instead.

Stop hunting for “AI words.” Most of them are just standard English that algorithms learned from us. One word doesn’t make copy synthetic — lazy patterns do.

Ditch word paranoia
Robust, seamless and leverage existed before ChatGPT. A single appearance isn’t proof of a prompt — it’s vocabulary. Purging useful words only weakens the writing.
Spot vocabulary stacking
One seamless is fine. Seamless, effortless, streamlined and innovative crammed into one sentence is where copy dies. Repetition is the culprit, not the word itself.
Match the room
Utilise works in a technical spec. On a homepage, use wins. Words aren’t inherently “AI” — they’re either useful or out of place.
Fix the substance, not the vocab
Swapping buzzwords won’t rescue empty copy. A cliché can work in a sharp, specific context. Simple words still sound robotic when they say nothing.

18 diagnostic categories

Score the draft against these. Drill into individual tells underneath.

#CategoryWhat it catches
1Word choiceAI-associated vocabulary
2Corporate languageInflated / formal wording
3Generic marketingClichés and empty claims
4Rhetorical patternsNot X/Y, rule of three, templates
5MetaphorsLandscape, ecosystem, journey…
6VaguenessAbstract / general language
7SpecificityMissing concrete information
8RepetitionWords, ideas, structures
9Sentence-levelRhythm and syntax
10Page architectureFormulaic organisation
11Conversational tells“Here’s the thing…”
12Manufactured personalityFake human voice
13Hype / evidenceUnsupported claims
14FormattingVisual AI patterns
15VoiceDistinctive human voice
16OriginalityOriginal thought / expression
17Information densitySubstance per sentence
18AuthenticityTruthfulness / real experience

What a cluster looks like

One paragraph, five tells. This is what “overuse” means in practice.

In today’s fast-paced digital landscape, our innovative platform empowers modern businesses to unlock greater efficiency and drive meaningful results at scale.
01

Word choice

AI-associated vocabulary. Score clusters and overuse — not single hits.

1.1 AI-associated verbs

leverage utilise harness facilitate foster empower enable elevate unlock unleash transform revolutionise streamline optimise maximise bolster enhance cultivate navigate accelerate amplify propel ignite drive champion showcase redefine reimagine align integrate implement deploy cater to resonate

1.2 AI-associated adjectives

robust comprehensive seamless cutting-edge innovative revolutionary groundbreaking powerful dynamic holistic multifaceted sophisticated transformative unparalleled exceptional remarkable compelling impactful meaningful strategic scalable agile versatile intuitive effortless frictionless vibrant exciting engaging insightful invaluable essential crucial pivotal paramount meticulous bespoke tailored world-class next-generation state-of-the-art future-ready forward-thinking

1.3 AI-associated nouns

innovation transformation optimisation efficiency scalability agility productivity collaboration connectivity accessibility flexibility visibility growth success excellence performance potential empowerment engagement alignment acceleration intelligence capability opportunity impact value complexity clarity confidence control

1.4 Inflated alternativesPrefer the plain form unless the formal one earns its place

utiliseuse
facilitatehelp
commencestart
endeavourtry
obtainget
numerousmany
additionalmore
approximatelyabout
demonstrateshow
providegive
requireneed
ascertainfind out
regardingabout
subsequentlylater
prior tobefore
in order toto
due to the fact thatbecause
a number ofseveral / many
at this point in timenow
in the event thatif
with regard toabout
is able tocan
02

Corporate language

Inflated and formal wording that adds weight without adding meaning. (See also 1.4 inflated alternatives.)

Latinate stack

Formal verbs where plain ones are clearer.

utilise · facilitate · commenceuse · help · start

Noun chains

Stacked abstractions with no actor.

solution implementation process optimisation

Prepositional bloat

Long prepositions for short ideas.

due to the fact thatbecause

Ability circumlocution

Three words where one works.

is able to / has the ability tocan
03

Generic marketing language

Clichés and empty claims that could sit on any site in the category.

2.1 Generic claims

drive growth drive efficiency drive engagement drive innovation drive results deliver results create value maximise potential unlock opportunities improve performance enhance productivity increase efficiency make an impact achieve success create meaningful impact deliver meaningful results

2.2 Generic transformation language

transform your business transform your workflow transform your operations transform your customer experience revolutionise the way you work redefine productivity redefine what's possible reimagine your workflow reimagine the future take your business to the next level unlock your full potential unleash your potential

2.3 Generic superiority

world-class industry-leading best-in-class cutting-edge state-of-the-art next-generation game-changing groundbreaking revolutionary unparalleled unprecedented extraordinary exceptional future-ready future-proof

2.4 Generic reassurance

we've got you covered we've got your back you're in good hands peace of mind rest assured worry no more we're here to help your success is our success
04

Rhetorical patterns

Templates AI reaches for when it needs structure without substance.

Contrast

Not X, but Y

“It's not just a tool. It's a transformation.”

Not only X, but Y

“Not only does it save time, but it also…”

X without Y

“Scale without complexity.”

Less X, more Y

“Less admin. More growth.”

Transformation & dual frames

from strategy to execution from data to decisions from planning to delivery from ideation to implementation from first click to final conversion reactive to proactive manual to automated complexity to clarity data to insight
Simple enough for small teams, powerful enough for enterprises Easy enough for beginners, powerful enough for experts creativity meets technology data meets intelligence simplicity meets power strategy meets execution humans meet AI

Whether / Imagine / What if

whether you're a startup or enterprise whether you're new to X or experienced whether you're looking to X, Y or Z Imagine a world where… Imagine being able to… Imagine if your team could… What if you could…? What if your team could…?
05

Metaphors

Environment, journey, construction, movement, change — and the literary clichés.

Environment

landscape ecosystem environment arena realm

Journey

journey roadmap pathway route destination

Construction

foundation cornerstone blueprint framework building blocks

Movement & change

propel accelerate navigate drive bridge move forward catalyst engine fuel unlock ignite

Literary clichés

tapestry rich tapestry intricate tapestry testament to at the heart of
06

Vagueness

A major scoring category. Core test: Can I replace the generic noun with something concrete?

Generic audiences

businesses organisations teams professionals users customers individuals modern businesses forward-thinking businesses

Generic problems

challenges pain points complexity inefficiencies bottlenecks obstacles demands pressures

Generic outcomes

success growth results impact value performance opportunities potential

Generic actions

improve optimise streamline enhance transform empower enable support facilitate

Generic objects

solution platform ecosystem framework approach methodology system tool offering
07

Specificity failures

What’s missing when the sentence sounds precise but isn’t.

Missing people

Role erased into a blob audience.

Businesses struggle with…RevOps leads spend Mondays…

Missing situations

“Manual processes” with no scene.

Manual processes slow teams downCopy-pasting from Salesforce into a spreadsheet

Missing mechanisms

Outcome with no how.

Improves efficiencyAuto-assigns leads by territory so SDRs don’t triage

Missing evidence

Assertion without proof.

Better results for customersCut onboarding from 14 days to 3 (n=40)

Missing consequences

Saved time that goes nowhere.

Save hours every weekSave two hours Fridays — enough to close the week clean

Missing context

Could be any industry.

Built for modern teamsBuilt for multi-clinic physio practices

Fake specificity

Precision theatre.

Up to 10x better performance*Cite the test, the baseline, the condition
08

Repetition

Words, ideas, benefits, structures, sections, CTAs.

Lexical

Same word repeated until it dulls.

Our platform… the platform… with this platform…

Semantic

Same idea restated in different clothes.

We save you time. You’ll work faster. Hours come back to your week.

Benefit chain

One benefit spun into three near-synonyms.

Save time → reduce workload → increase productivity

Structural

Same sentence machine, new nouns.

With X, you can Y. With X, you can Z. With X, you can…

Section

Every block: heading → claim → three bullets → soft close.

Problem / Solution / Benefits — repeated four times

CTA echo

Mini-CTA at the end of every section.

Ready to start? · Get started today · Start your journey
09

Sentence-level tells

Rhythm, symmetry, fragments, openings, overqualification.

Sentence symmetry

“Fast, flexible and powerful.”

Rule-of-three saturation

Three benefits everywhere.

Uniform sentence length

Same approximate length, page after page.

Excessive short sentences / fragments

Less admin.
More growth.
Better results.

Repeated openings

Our platform… Our platform… Our platform…

Overly neat cadence

Everything equally polished and balanced.

Overqualification

may might could often generally typically potentially arguably in many cases to some extent depending on
10

Paragraph & page architecture

Formulaic organisation at section and page level.

The AI blog structure

A fixed pipeline regardless of the topic.

Hook → problem → explain → solution → 3 benefits → summary → CTA

Identical section structures

You can predict the next block before you read it.

H2 → 40 words → 3 bullets → soft close (×5)

Over-sectioning

Headings doing the work of sentences.

Eight H2s on a one-screen product page

Over-signposting

Announcing structure instead of using it.

“First, we’ll explore… Next, we’ll look at… Finally…”

Manufactured conclusions

Every block ends with the same bow.

“The result?” · “The takeaway?” · “The key is…”

Information symmetry

Minor points get the same airtime as the real differentiator.

Equal word count per feature, including the trivial ones
11

Conversational AI tells

Artificial hooks, engagement, reassurance, urgency.

Artificial hooks

Here's the thing… Here's what you need to know… Here's the kicker… Here's where it gets interesting… Here's the catch… Here's what most people miss…

Artificial engagement

What do you think? Agree or disagree? Have you experienced this? I'd love to hear your thoughts. What's your biggest challenge?

Artificial reassurance

You're not alone. And that's okay. We've all been there. You shouldn't have to…

Artificial urgency

Now is the time. The time is now. Don't get left behind. Don't let competitors get ahead.
12

Manufactured personality

Fake vulnerability, discovery, experience, authority.

Fake vulnerability

I'll be honest… · I used to think… · I made a mistake… · Here's what nobody tells you…

Fake discovery

This changed how I think about… · That's when I realised… · It made me realise…

Fake personal experience

“A client called me…” · “I was speaking to a founder…” · “Last Tuesday…”

Fake authority

experts agree · studies show · industry leaders know · research proves

…without identifying the evidence.

13

Hype vs evidence

Score the claim-to-proof ratio. High-risk claims need evidence.

revolutionary transformative unprecedented exceptional significant dramatic massive enormous remarkable powerful meaningful

Where’s the evidence?

If the claim is high-risk and the proof is missing, the score should reflect that — whether or not the vocabulary is “AI-ish”.

14

Formatting tells

Visual patterns that often travel with generated drafts.

excessive bold excessive italics excessive bullet points one-line paragraphs emoji-heavy formatting repeated colons em-dash overuse parentheses stacking rhetorical-question headings excessive headings identical formatting patterns
15

Voice

Beyond detection: does this sound like a believable human author?

  • A recognisable point of view
  • Appropriate informality
  • Natural contractions
  • Natural vocabulary
  • Personality
  • Appropriate humour
  • Genuine opinion
  • Industry fluency
  • Audience awareness
  • A believable human author
16

Originality

The positive side of humanisation — what to reward, not only what to flag.

  • Original observations
  • Uncommon examples
  • Genuine opinions
  • Specific customer insights
  • Unexpected comparisons
  • Distinctive phrasing
  • Real-world details
  • Company-specific knowledge
  • Useful disagreement
  • Interesting anecdotes
  • Information competitors wouldn’t naturally have
17

Information density

How much useful information each sentence delivers.

Low density

Our innovative platform empowers modern businesses to unlock greater efficiency.

High density

Connect Salesforce to Snowflake and let sales reps pull customer data without asking an analyst.

Look for: who + what + how + why + evidence + consequence.

18

Authenticity

Separate from “AI-ishness”. Is the writing true to experience and evidence?

  • Are anecdotes real?
  • Are customer claims verifiable?
  • Are numbers sourced?
  • Are opinions genuinely held?
  • Is personal experience genuine?
  • Are testimonials real?
  • Are claims appropriately qualified?
  • Is the brand actually capable of doing what it says?

This list will keep growing. Spotting a tell doesn’t mean the copy is bad — it means AI may have had a hand in it. The job is to decide whether that pattern is earning its place.

From library to scorecard

These 18 categories feed the Humanisation Methodology: diagnose the tells, then rewrite with judgement.

See the methodology →