// AI BRAND VOICE & PERSONA

The complete AI banned-word library (kill every AI tell)

120+ phrases that flag content as AI-written — hedge words, tricolons, marketing speak, vague authority, closing summaries — with category-organized copy-paste lists.

The direct answer

The complete AI banned-word library contains 120+ phrases organized into 8 categories: hedge words, AI bridge phrases, closing summaries, marketing speak, vague authority, em-dash overuse, tricolons, and "not just X but Y" constructions. Each category is a copy-paste list ready for your Persona Brief banned-words section. Banning these phrases at the output-time gate (not just at the prompt level) is what makes AI content stop sounding like AI.

Generic AI output has fingerprints. Every base model — GPT-5, Claude 4, Gemini 2 — has the same handful of phrases it falls back on when it cannot decide what to write. Banning those phrases is the single highest-leverage move in any Persona Brief.

This is the complete library, organized by failure category. Copy-paste the categories that match your industry into your brief.

Category 1: Hedge words

Models hedge because hedged claims are harder to prove wrong in training data. Humans who actually know the topic do not hedge.

  • arguably
  • it is worth noting that
  • one could argue
  • broadly speaking
  • generally speaking
  • in many cases
  • tends to
  • can sometimes
  • may often
  • often considered
  • is typically
  • is usually
  • is generally
  • is largely
  • might be
  • could potentially
  • is essentially

Replacement strategy: drop the hedge entirely. "Most teams" not "Many teams tend to." If a hedge is truly required, replace with a specific qualifier: "In the 4 cases we tested..."

Category 2: AI bridge phrases

Transitions models use when they cannot find a real connection between two ideas.

  • not just X but Y
  • this is more than just
  • what makes this special
  • in addition
  • furthermore
  • moreover
  • on top of that
  • beyond that
  • in essence
  • fundamentally
  • at its core
  • when it comes to
  • as we explore
  • as we examine
  • as we consider

Replacement strategy: cut the bridge and start the next sentence with a noun or verb. The reader does not need to be told a new thought is coming.

Category 3: Closing summaries

Models close with a recap because their training data rewards it. Human writers usually close with a concrete line — a callback, a provocation, or a specific next action.

  • in conclusion
  • ultimately
  • to summarize
  • at the end of the day
  • wrap up
  • final thoughts
  • to sum up
  • in summary
  • all in all
  • overall
  • taking everything into account

Replacement strategy: delete the entire closing paragraph if it summarizes. Replace with one concrete sentence — a callback to the opening, a specific next action, or a provocation.

Category 4: Marketing speak

The biggest category. These phrases are corporate jargon that AI inherited from training on marketing copy. Audiences tune out within 3 seconds.

  • in today's fast-paced world
  • in today's digital age
  • in today's competitive landscape
  • leverage
  • unlock
  • dive deep
  • deep dive
  • game-changer
  • game-changing
  • revolutionize
  • transformative
  • paradigm shift
  • next-level
  • seamless
  • frictionless
  • cutting-edge
  • state-of-the-art
  • best-in-class
  • world-class
  • industry-leading
  • mission-critical
  • turbocharge
  • supercharge
  • streamline
  • optimize
  • maximize
  • empower
  • enable
  • transform
  • elevate
  • robust
  • comprehensive
  • holistic
  • innovative
  • thought leader
  • thought leadership
  • subject matter expert

Replacement strategy: replace with the plain-language alternative. "Leverage AI" → "use AI." "Streamline workflows" → "make workflows simpler." If the plain-language version sounds empty, the original was empty too — cut the whole sentence.

Category 5: Vague authority claims

Phrases that sound authoritative but cite nothing.

  • studies show
  • research suggests
  • experts agree
  • data confirms
  • it is well known that
  • it is widely accepted that
  • it is no secret that
  • many believe
  • most agree
  • industry consensus is
  • common wisdom says
  • conventional thinking suggests

Replacement strategy: cite a specific study, name a specific expert, or drop the claim. Vague authority is worse than no authority — it signals laziness.

Category 6: Em-dash overuse (cap, not ban)

Em-dashes are not banned outright — they have legitimate uses. But models overuse them at 5-10x human rates. Cap them in the brief:

Em-dash limit: 1 per 300 words.

Replacement strategy: convert most em-dashes to periods or commas. Reserve em-dashes for parenthetical asides that would otherwise need full parentheses.

Category 7: Tricolons (rule of three)

Three-item lists are a base-model reflex. "Fast, reliable, and scalable." "Easy to use, easy to learn, and easy to love." Sprinkled occasionally these are fine. Three tricolons per paragraph is a dead giveaway.

Tricolon limit: 1 per 500 words.

Replacement strategy: convert most tricolons to two-item lists ("fast and reliable") or four-item lists ("fast, reliable, scalable, and observable") or single punchy claims ("fast — that's it").

Category 8: "Not just X but Y" structure

The single most over-used AI sentence structure. Ban the literal phrase "not just."

  • It is not just faster, it is fundamentally different.
  • This is not just a tool, it is a workflow.
  • We are not just a platform, we are a partner.

Replacement strategy: drop the "not just" entirely and assert the second clause directly. "It is fundamentally different." "It is a workflow." "We are a partner." Direct claims always beat escalation patterns.

Industry-specific banned words

Add these based on your industry:

SaaS / tech

  • synergize
  • synergistic
  • circle back
  • low-hanging fruit
  • value-add
  • cross-functional
  • agile-first
  • data-driven (when overused)

Real estate

  • motivated seller
  • investment opportunity
  • wealth-building
  • passive income (when overused)
  • cash-flowing asset

Coaching / consulting

  • mindset shift
  • limiting beliefs
  • next-level mindset
  • breakthrough
  • transformative journey
  • unlock your potential
  • 10x your

Health / wellness (use with extra caution)

  • wellness journey
  • holistic approach
  • natural solution
  • gentle yet effective

How to use the banned-word library

  1. Copy the categories that match your industry into the Section 3 of your Persona Brief.
  2. Add 5-10 words per week from your own edits — the ones you keep deleting from AI output.
  3. Enable the brand-safety gate (Gate 4 in /autonomous/quality-gates) to enforce them at output time.
  4. Review the list every 3 months. Remove words that no longer slip through. Add new ones that do.

The list is a living document. A mature Persona Brief typically ends up with 150-250 banned words after 6 months of refinement.

Frequently asked questions

Will banning all these words make my content sound stilted?

No, if you replace banned phrases with concrete alternatives. The stilted version comes from prompting around the banned word without replacement. The right approach: ban the phrase, give the model a structural rule for what to do instead (e.g. "cut closings entirely, replace with one concrete sentence").

Can I get the list of banned words as a JSON file?

Yes — Kompozy ships a default banned-word list per Persona Brief that you can edit. The full library above is the starter set. Your custom additions stack on top.

Do AI detection tools look for these phrases?

Some do, some do not. AI detection is unreliable across the board. The right framing is not "evade detection" but "remove generic AI feel." Readers detect AI long before tools do — banning these phrases improves reader experience whether or not it affects detection scores.

Should I ban specific brand words too?

Yes — add competitor brand names (when you do not want them surfaced), legal-sensitive terms (per industry compliance), and any internal jargon you do not want public. The brand-safety gate enforces all of them equally.

How aggressive should I be with the banned list?

Aggressive. Over-banning makes the gate reject more outputs (which trigger regeneration). The cost of over-banning is regen latency. The cost of under-banning is shipped slop. Always over-ban.

Related guides in AI Brand Voice & Persona

Adjacent clusters

  • Autonomous Content CreationMost "autonomous" AI content is slop. Here is how 4 quality gates make autopilot output indistinguishable from manually-approved content — and the exact 14-day ramp to flip the switch safely.

← Back to AI Brand Voice & Persona overview · Start a free trial → · See pricing