137 phrases across 5 structural archetypes that flag content as AI-written. Drawn from the anti-AI-tell rules written into Kompozy's generation prompts, the same rules every text generation runs under.
The 2026 AI Tells Index lists 137 phrases across 5 structural patterns that make writing read as AI: hedge words, tricolons (lists of three), pseudo-philosophical bridges, authority hand-waves, and emotional thinness. It is a curated index, not a detection study. One phrase proves nothing, because the signal is how densely they cluster. Fix each tell by replacing it with a specific detail, not by deleting it.
Key takeaways
137 phrases across 5 archetypes, counted from the lists on this page.
Concentration is the signal: one hedge is fine, a hedge in every sentence is not.
Replace a tell with a specific detail instead of just deleting it.
Re-check your writing after each major model update, since new models bring new tells.
How was the AI Tells Index built?
This is not a study. It is a curatorial index — an opinionated ranking of AI-tell phrases organized by the structural archetype that produces them. The methodology behind the index:
Source corpus. The phrases were collected from three sources: (a) the anti-AI-tell rules written into Kompozy’s generation prompts, which tell the model which words and constructions to avoid, (b) public LLM output across GPT-4-family, Claude-3-family, and Llama-3-family models, generated from generic content prompts during product development, (c) feedback from operators who reviewed autopilot outputs during the calibration window before flipping to autopilot.
Classification rubric. Each phrase was assigned to one of 5 archetypes based on the cognitive shortcut the model takes when producing it. Archetypes were derived inductively from the corpus, not pre-defined.
Tell strength. Phrases within each archetype are loosely ordered by how strongly they signal AI generation when they appear in isolation. A phrase like "It is worth noting that" at the start of a paragraph is a stronger AI tell than "Often" mid-sentence — both are hedges, but one is more diagnostic.
What this index is NOT. It is not a statistical analysis of AI-detection-tool performance. It is not a claim that any specific phrase guarantees AI authorship. Humans use all of these phrases sometimes. The index identifies the patterns that, when concentrated in a single piece of writing, produce the recognizable "this was written by AI" feeling.
Why does AI-sounding content underperform?
Content that reads as AI costs you with readers and with search. People discount claims that sound generic and are less likely to share them, and Google’s guidance warns that mass-produced pages without added value can break its scaled content abuse policy. Banning the 5 archetypes is not about hiding that AI was involved — it is about producing content that earns the same trust as the best human writing, regardless of how it was produced.
Kompozy writes banned-phrase rules into its generation prompts, so the model is told up front which words and constructions to avoid. Nothing scans the finished draft for them, which is why the self-check below still matters.
What are the 5 archetypes of AI tells?
The 5 archetypes are hedge words, tricolons, pseudo-philosophical bridges, authority hand-waves, and emotional thinness. Click any archetype to jump to its full phrase list and structural analysis.
LLMs are trained to avoid claim-confidence because confident claims trigger hallucination risk during RLHF. The model learned that hedging is "safer." Humans confident in their position do not hedge — they assert. That is why hedges show up so often in model output.
The phrases (30)
It is worth noting that
It is important to consider
It might be useful to
One could argue that
In many cases
Generally speaking
To some extent
It is often the case that
In a sense
More or less
It depends
It varies
It largely depends on
Broadly speaking
In general
For the most part
In most situations
It is also worth mentioning
It should be noted
It is generally accepted that
Some might say
There are those who argue
Could potentially
May or may not
Tends to
Often
Sometimes
Frequently
Typically
Usually
The fix
Replace every hedge with a specific instance or a confident assertion. "It is often the case that X" becomes "X happened on the last three projects I shipped." Specificity beats hedging on every dimension: trust, engagement, memorability.
2. Why do tricolons (the rule of three) read as AI?
Why this archetype lands
LLMs love three-item lists because they pattern-match against rhetorical training data (Lincoln, Churchill, Aaron Sorkin). Ask it about almost anything and it reaches for a three-item structure. Real writers use tricolons sparingly because lists of three lose specificity at scale.
The phrases (23)
Faster, cheaper, and better
Simple, scalable, and effective
Efficient, reliable, and powerful
Engaging, informative, and valuable
Authentic, genuine, and real
Innovative, creative, and bold
Powerful, intuitive, and elegant
Smart, simple, and seamless
Bold, fresh, and original
Insightful, actionable, and clear
Robust, scalable, and secure
Modern, clean, and minimal
Strategic, tactical, and operational
Vision, mission, and values
People, process, and technology
Plan, do, and review
Engage, educate, and entertain
Awareness, consideration, and decision
Strategy, execution, and measurement
Past, present, and future
Quality, quantity, and consistency
Time, money, and effort
Mind, body, and soul
The fix
Cut the third item. If the third item is needed, the first two were wrong. "Faster, cheaper, and better" becomes "Cheaper without losing quality" — a real claim with a real trade-off. The discipline is to commit to two dimensions per sentence, not three.
3. Why do pseudo-philosophical bridges read as AI?
Why this archetype lands
LLMs produce these because the training data is dense in essay-form prose. Real writers either skip transitions entirely (paragraph break = transition) or use specific, content-bearing transitions. Pseudo-bridges signal "I am about to say something" rather than actually saying it.
The phrases (26)
In an increasingly digital world
In today's fast-paced environment
In the modern landscape
In the ever-evolving world of
In this day and age
As we navigate the complexities of
When it comes to
At the end of the day
When all is said and done
In the grand scheme of things
It is no secret that
It goes without saying
Needless to say
That being said
With that in mind
Having said that
On the other hand
It is clear that
It is evident that
Without a doubt
It cannot be denied that
There is no question that
In light of
In view of
In the context of
It is no surprise that
The fix
Delete the bridge entirely. Start the sentence with the content. "In an increasingly digital world, marketing is hard" becomes "Marketing is hard." The bridge rarely adds information. The reader already knows we are in a digital world.
4. Why do authority hand-waves read as AI?
Why this archetype lands
LLMs invoke vague authority because real authority claims require citations the model often cannot produce. "Studies have shown" is the AI version of "trust me, bro" — a confidence-projection without underlying evidence. Real writers either cite the specific study or do not invoke study-evidence.
The phrases (24)
Studies have shown
Research suggests
Experts agree
According to data
It is well known
Many believe
It is widely accepted
Industry leaders say
The data is clear
Research consistently shows
Studies indicate
Evidence suggests
It has been proven
According to recent studies
Research has demonstrated
Numerous studies confirm
A wealth of research
Experts in the field
Authorities in the space
Top performers
High-performing teams
Leading companies
The most successful
Best-in-class
The fix
Either cite the specific study by name + year, or skip the authority claim entirely. "Studies have shown that X" becomes "The 2024 Backlinko ranking factors study found X." If you cannot cite, the claim was probably weaker than the hand-wave suggested.
5. Why does emotional thinness read as AI?
Why this archetype lands
LLMs simulate emotional language by reaching for clinical descriptors of emotion rather than performing the emotion. The result is technically grammatical but flat — "exciting" and "delightful" and "passionate" carry no specific texture. Real emotional language is concrete (a memory, a sensation, a stake) not labeled.
The phrases (34)
Exciting
Delightful
Passionate
Game-changing
Mind-blowing
Revolutionary
Transformative
Inspiring
Empowering
Cutting-edge
State-of-the-art
Best-in-class
World-class
Top-notch
Top-tier
Next-generation
Next-level
Unparalleled
Unmatched
Phenomenal
Incredible
Amazing
Wonderful
Fantastic
Outstanding
Exceptional
Remarkable
Extraordinary
Truly remarkable
Heartfelt
Authentic
Genuine
Resonates deeply
Speaks volumes
The fix
Replace the emotion label with the cause of the emotion. "It was a game-changing experience" becomes "I rewrote the pricing page the night after that call." Emotion comes from the specific concrete; the label kills the emotion every time.
How do you apply this index to your writing?
Run a banned-word lint on every draft. Manual: paste your draft into a find-and-replace tool with this index as the search set. Automated: run a script that flags any phrase from this index in the finished draft.
Replace, do not delete. Every banned phrase is a placeholder for missing specificity. When you cut "It is worth noting that," the replacement is a specific instance, not nothing.
Track concentration, not occurrence. One hedge word in a long piece is fine. A hedge in every sentence of a short paragraph is the AI feel. The signal is concentration.
Calibrate to your voice. Some industries (academic writing, legal copy) legitimately use hedge words. The Persona Brief overrides the universal list with voice-specific exceptions.
Re-check after model updates. New model releases bring new tells, so re-check your output after each major model update.
AI Brand Voice cluster — the full topic cluster on making AI sound like you instead of like ChatGPT.
How do you cite the AI Tells Index?
Ameen, M. (2026). The 2026 AI Tells Index: 5 archetypes and 137 phrases that flag content as AI-written. Kompozy. https://kompozy.io/research/ai-tells-index
How often is the AI Tells Index updated?
This index is updated as new model versions ship and new tells emerge. Subscribe via the Kompozy changelog to be notified of revisions.
What does this look like in Kompozy?
A persona tweet graphic generated in the Kompozy workspace, the kind of short text post these rules are meant to clean up. It shows the format only.
Real output · Kompozy Persona tweet format · from the Kompozy workspace
Who is this for, and who should skip it?
Best for:
Writers and editors cleaning up AI-assisted drafts
Teams building a banned-phrase list into prompts or style guides
Anyone who wants a quick self-check before publishing
Not ideal for:
Anyone trying to prove a text was AI-written. The index is not a detector
Academic or legal writing, where some hedging is expected
People hoping to fool a detector. Edit for a real voice instead
Frequently asked questions
What are AI tells in writing?
AI tells are recurring structural patterns that flag content as machine-generated. This index groups them into 5 archetypes: hedge words and softeners, tricolons (lists of three), pseudo-philosophical bridges, authority hand-waves, and emotional thinness. Concentrated together in one piece, they produce the recognizable "this was written by AI" feeling.
How many AI tell phrases does the index list?
The index catalogs 137 phrases across the 5 archetypes, loosely ordered within each archetype by how strongly they signal AI generation when they appear in isolation.
How do I make AI writing sound less like AI?
Replace each tell rather than just deleting it — every banned phrase is a placeholder for missing specificity. Track concentration, not occurrence: one hedge in a long article is fine, but a hedge in every sentence is the AI feel. Building banned phrases into your prompts and your editing pass is the structural defense.
Is the AI Tells Index a detection-accuracy study?
No. It is a curatorial, opinionated index, not a statistical analysis of detection-tool performance. It does not claim any single phrase guarantees AI authorship — humans use all of these phrases sometimes; the signal is concentration.
Where do the phrases in the index come from?
They were collected from three sources: the anti-AI-tell rules written into Kompozy's generation prompts, public LLM output across GPT-4, Claude-3, and Llama-3 family models from generic prompts, and operator feedback during autopilot calibration. Archetypes were derived inductively from that corpus.
How do we know this?
We counted the five phrase lists on this page on 2026-10-23 (30, 23, 26, 24, and 34 phrases, 137 in total) and corrected the old count of 147. We removed unsourced figures from the archetype notes and checked the Google claim against Google Search Central.