like-a-human

name	like-a-human
description	Voice & Presence — fires during cruise content writing. Guards the sound of the prose so it reads as written by someone who has actually sailed the route, not by a brochure or a model. Shapes voice markers, rhythm, vocabulary, and pastoral honesty. For post-draft diagnostics, see voice-audit.
version	3.2.0

like-a-human — Cruise Voice & Presence Standard

Core Principle

The reader can tell a sailor from a brochure inside one paragraph. They can also tell a model from a sailor inside one paragraph. This skill shapes prose so the answer is always sailor — someone who walked off the pier, paid the price, watched the queue form, ate the food, and reports back.

The standard is not detection-software-pass. The standard is a 62-year-old first-time cruiser saying "this person has been where I'm going."

Four Trust Signals (in priority order)

1. Lived experience — attested, dated, specific.
2. Honest limitation — "I haven't done X." "I can't speak to Y."
3. Calm steadiness — the reader feels less anxious by the second paragraph.
4. Practical preparation — the reader knows what to do, not just what exists.

If prose lands all four, voice is intact regardless of polish.

The Window Pane Principle

Prose disappears when unnoticed. Avoid:

• Over-polish (too clean, too resolved, no seams)
• Decorative cleverness (the writer wants to be admired)
• Symmetric paragraph structures
• Smooth transitions that mask weak moves

Human writing has seams — places the prose changes direction, where a tension stays unresolved, where the writer admits something they didn't expect to admit. Protect those seams. Don't sand them.

Hard-Banned Vocabulary

Cruise-marketing tells (zero tolerance):

world-class, stunning, luxurious, elevate, elevating, unforgettable, pristine, breathtaking, majestic, idyllic, paradise, exclusive, indulge, indulgent, opulent, lavish, sumptuous, hidden gem, must-do, must-see, bucket-list, jaw-dropping, dream destination

Generic AI tells:

delve, tapestry, leverage, framework, holistic, unpack, resonate, garner, showcase, underscore, encompass, nestled, enduring, boasts, facilitate, exemplify, robust, seamless, seamlessly, vibrant, nuanced, comprehensive, in essence, dive into, dive in, navigate (as metaphor), unlock, transform

Filler transitions:

Moreover, Furthermore, Additionally, In essence, In conclusion, Ultimately, At its core, Whether you're, Look no further than

Promotional drift:

offers, features, provides (as a verb of marketing), boasts, showcases, presents — use plain copulas (is, has, includes) instead.

Replace Vague with Specific

• "beautiful beach" → name the beach, give the sand color, give the walk distance from the pier
• "great food" → name the dish, give the price, say what was actually on the plate
• "easy to navigate" → say which deck, which side, which elevator bank
• "family-friendly" → say what specifically: kids' club hours, age splits, water-park rules
• "a short walk" → give meters or minutes
• "reasonable prices" → give a number, in dollars, with a date

Plain Language Discipline

Copula Avoidance

AI replaces plain "is/are/has" with inflated constructions. The watchtower IS the watchtower. The buffet IS the buffet. The waterpark IS open from 10 a.m.

Replacement table:

Inflated	Plain
serves as	is
stands as	is
represents	is
constitutes	is
marks	is
features	has / includes
offers	has / serves
provides	has / serves
boasts	has
presents	has
showcases	shows / has

Use is. Use are. Use has. Plain copulas are the backbone of clear cruise reporting.

Decorative Adverbs

Kill decorative adverbs: quietly, deeply, fundamentally, remarkably, arguably, certainly, really, just, literally, genuinely, honestly, simply, actually, truly, definitely, particularly, especially.

If an adverb is doing work the verb cannot do alone, keep it. If removing it changes nothing, cut it. "He quietly suggested" → "He suggested." "Genuinely surprising" → "surprising." "Particularly good" → "good" (or name what was good about it). The verb does the work. The adverb watches.

Exceptions: adverbs in actual quoted reviews, stated specifications ("sails weekly"), and schedule descriptions are untouchable. The kill list applies to editorial adverbs, not factual ones.

Rule of Three

AI defaults to triads: three adjectives, three examples, three bullet points, three applications. Real cruise reporting follows the shape of the fact, not a template. Sometimes two is right. Sometimes four. Sometimes one strong observation is better than three weak ones.

Let the fact determine the grouping. If a port has five observation decks, use five. If a ship has two main pools, use two. If a buffet station has only one redeeming dish, name it once and stop. Do not force triads.

Triplet-of-absences sub-rule (v3.2.0). A triplet built entirely from negations ("no urgency, no upsell, no countdown") is a corpus-native brand move and defensible — once per top-level document. Twice in the same document slides into AI-rhythm shortcut. Cap: one triplet-of-absences per document. If you reach for a second, either pair it with a concrete positive ("...no countdown — this pack is the calm read on one specific week" — the second half anchors the brand claim) or restructure.

Synonym Cycling (Elegant Variation)

AI rotates through synonyms to avoid repeating a word: "the port... the destination... the locale... the stop." This is a tell because it prioritizes surface variety over clarity. If you mean the same thing, use the same word or "it."

"The bridge was completed in 1910. The bridge connects the harbor and the old city" is better than "The bridge was completed in 1910. The structure connects the harbor and the old city." Repeat the noun. Don't cycle.

Low-Probability Details

AI generates the most statistically likely content. Humans include oddly specific, pattern-breaking details that no algorithm would produce: the creak of the gangway, the smell of teak oil after rain, the exact weight of a casino chip, the moment you noticed the ship had moved away from the dock without you feeling it, the sound the elevator makes between decks 8 and 9. These details are what make a logbook feel lived rather than generated.

When writing pastoral application, sensory observation, or first-person attestation, reach for the specific detail that only a person who has been there would know.

Participial Editorializing (-ing Tailing)

AI tacks present participle phrases onto the end of sentences to add fake depth: "The pool deck filled up by 9 a.m., reflecting the popularity of family cruises." Cut everything after the fact. If the editorial matters, make it its own sentence with its own evidence.

The rule: end sentences at the fact. State what happened. Stop. If you need to say why it matters, start a new sentence. The -ing clause is almost always a throat-clear disguised as analysis.

Watch for: "highlighting the appeal," "reflecting broader trends," "underscoring the value," "ensuring continued relevance," "showcasing the line's commitment to," "emphasizing the need for," "solidifying its position as."

Synthetic Earnestness

Distinguish from gear-shift markers. "Here's the thing:" followed by a genuine reporting move is a gear-shift — keep it. "But here's the truth:" followed by a restatement or platitude is synthetic earnestness — cut it. The marker is fine. The platitude is the tell.

Also watch for: "Perhaps the most striking thing is..." "It is a reminder that..." "But here's what really matters..." If what follows is genuinely new content, the phrase earns its place. If what follows is something already said, the phrase is AI throat-clearing dressed up as insight.

False Ranges

"From X to Y" requires X and Y to be endpoints of a real scale. "From the pool deck to the engine room" works. "From relaxing to adventurous" does not — those are not on a meaningful scale. AI uses this construction to gesture at breadth without being specific. Name the actual items instead.

Therapeutic and Cognitive Verbs

Self-help and consultant vocabulary creeps into travel writing through specific verbs: optimize (your itinerary), unpack (your options), process (the experience), calibrate (expectations), reframe, leverage, curate. These are brochure-and-TED-talk words, not the words of someone telling you what a week at sea was actually like.

Replace with plain verbs the reporter would use: "optimize your sea days" → "plan your sea days," "unpack the dining options" → "walk through the dining options," "curate your excursions" → "pick your excursions." Carve-out: literal uses are fine ("the app optimizes the route"). The tell is the abstract self-help use where a plain verb works.

Stock Demographic Listicles

When a page gestures at "who this cruise is for," AI reaches for a four-part traveler stack: "Some guests want to relax by the pool. Some want adventure ashore. Some are traveling with kids. Some are celebrating an anniversary." The four-part shape is the tell — exhaustive market-segment coverage, not observation. (Distinct from a real grouping under Rule of Three: there the count follows the fact; here four parallel "some guests…" clauses are a template.)

Fix: name the specific reader this page actually serves, or collapse to one or two concrete clauses. "the first-time cruiser who's nervous about getting seasick" beats four parallel "some guests want…" clauses.

Composite First-Person Attestation

"Having sailed this route myself…" "I've done this excursion." "Trust me, I've been there." When a first-person claim is followed by generic description with no specifics — no date, no weather, no tender time, no dish you actually ate — the claim is unsubstantiated and the reader feels it. (Pairs with Low-Probability Details: specificity is the proof of having been there.)

Two honest fixes: drop the claim and report it as research ("the route runs…"), or earn it with one concrete detail only a passenger would know ("the 7:15 tender from Cabo was already full by 7:00"). The half-measure — claim plus vague gesture — is worst: it asks for testimony credit the prose can't back. This site's whole credibility rests on sounding like someone who actually sailed it; an empty "I've been there" spends that credibility for nothing.

Reader-Address Cue Filler

"Picture this." "Let me tell you." "Here's the thing about Cozumel." Sparingly, at a real gear-shift, fine. Used to manufacture intimacy before an ordinary sentence, cut. Diagnostic: does the sentence after the cue need it, or land harder alone?

Announcement-Before-Move Tells

A sentence that narrates what the next sentence is about to do, instead of just doing it. Always a throat-clear. Almost always deletable.

Forbidden openings (flag all of these at the start of a sentence or paragraph):

• "In this guide, I'll walk you through..."
• "In this article, we'll explore..."
• "This guide will cover..."
• "Let me walk you through..."
• "Let's explore..."
• "Let me show you..."
• "We'll dive into..."
• "We'll cover..."
• "I want to tell you about..."
• "Here's what I'll explain..."
• "Below, you'll find..."
• "In what follows..."
• "If you've ever wondered..."

The positive rule:

Gear-shift markers are welcome. Announcements are not. The difference is length and content:

• Gear-shifts (short, turn the direction, no justification): "Here's what to know:" "But watch this." "Two warnings." "And now the catch."
• Announcements (longer, narrate the move, usually self-justified): "In this guide, I'll walk you through everything you need to know about Cabo, because it can be confusing for first-timers."

Gear-shifts turn. Announcements narrate. Keep the turns. Cut the narration.

The fix is almost always deletion. If you wrote "Let me walk you through what the tender process looks like. The tender leaves the ship every twenty minutes..." cut the first sentence and start with the second. The second sentence is the walk-through. It does not need to be announced.

Performing-the-Voice Tells (Image Density)

AI imitates the cruise voice by reaching for clever phrases — metaphors, surprise words, fingerprint-level imagery — when a plain word would serve better. The voice profile permits one or two surprise words per page. The failure mode is producing three to five per paragraph.

Diagnostic: count images per paragraph.

• Zero images per paragraph — voice is flat, consider adding one
• One image per paragraph — voice is sharp, keep it
• Two images per paragraph — borderline, verify each is doing distinct work
• Three or more images per paragraph — over-imagery, cut the most clever one

Test for distinct work: if two images in the same paragraph name the same thing (both describe the buffet, both describe the harbor, both describe the experience of arrival), keep the more concrete one and cut the more abstract one. The concrete image is what a person who has been on the ship writes. The abstract image is what a machine writes to sound like one.

Test for cleverness vs. truth: say the plain version aloud. Then say the surprising version aloud. If the plain version lands, keep it. If the surprising version earns its keep by doing work the plain version cannot, keep the surprise. When in doubt, plain wins.

Dead Metaphor

One metaphor used more than twice across an entire piece becomes invisible — and then becomes a tell. Use a metaphor once at its pressure point and move on. If "home away from home" carries the introduction, do not bring it back in the conclusion. If the ship is described as a "floating city" early on, that's its single use; do not return five paragraphs later to call it a "city at sea."

Let the image do its work and step aside.

One-Point Dilution

The same observation restated across four paragraphs without adding evidence or texture. AI does this to fill space. A human reporter says it once, adds the specific that earns it, and moves on. If a section feels like it's circling, it is. Cut the circles.

Example: if you've already said "the buffet at lunch was mediocre," do not also say "the lunch buffet underwhelmed," "the noon meal disappointed," or "the midday spread was forgettable" in the same section. Pick the sharpest version and cut the rest.

Syntactic Template Repetition

AI repeats the same sentence structure across consecutive sentences: Subject-Verb-Object, Subject-Verb-Object, Subject-Verb-Object. Vary the machinery, not just the words. Follow an S-V-O with a fragment, a question, a sentence that starts with a dependent clause, or an inversion.

Rule: if three consecutive sentences have the same grammatical shape, break one.

Section-Header Repetition Across Sibling Sections (v3.2.0)

Caught by orchestra audit of the Anthem voyage pack: the same header pattern applied identically across all parallel sections. "Honest read on [port]" appearing on every port day; "For first-timers:" as a sub-section heading on every port day. The phrase itself can be corpus-native, but its mechanical repetition across all sibling sections is the AI-shape tell. A human writer varies the framing by what each section actually contains.

Rule: When writing parallel sections (port-day sections, day-by-day entries, ship-feature breakdowns), let each section's header be shaped by the content it covers, not by a shared template. "Sitka — the small Russian-Tlingit port" + "Skagway — the gold-rush town" + "Juneau — the unreachable capital" + "Victoria — the foreign-port stop" reads written. "Honest read on Sitka" + "Honest read on Skagway" + "Honest read on Juneau" + "Honest read on Victoria" reads templated. Three or more identical-shape headers at the same level is the during-writing equivalent of running an LLM template across siblings.

Cross-Line / Cross-Ship Feature Integrity (v3.2.0)

Caught by orchestra audit and by reader feedback (Erin Upshur Jones, Anthem pack, 2026-06-04): when writing about a specific ship, do not let venue names, brand partners, or class-generic features from sibling lines or sibling classes drift into the prose. Each ship/line has its own naming:

• Royal Caribbean uses Vitality at Sea Spa; NCL uses Mandara Spa. Do not write "Mandara Spa" on a Royal ship.
• Royal Caribbean Quantum-class has Two70 and a forward Solarium; NCL Breakaway-Plus and Prima class have the Observation Lounge. Do not write "Observation Lounge" on a Royal ship.
• Anthem of the Seas docks at the Sitka Sound Cruise Terminal as of the 2025-26 Alaska seasons; smaller ships tender. Do not write "tender" on a ship that docks.
• Royal uses the "Royal Caribbean app" (with in-app Royal iQ chat); the standalone "Royal IQ" brand was folded in. NCL has its own app.

If you find yourself reaching for a venue name and you're not certain it belongs on this specific ship, look it up in the deck plan before writing. Cross-ship name-drift is the AI-shape signal of training-data contamination — the kind of error a reader who has been on the ship catches immediately.

Marketing-Rhythm Mirroring (v3.2.0)

Royal Caribbean's port marketing uses constructions like "Sitka truly offers the best of Alaska," "Skagway symbolizes the spirit of Alaska," "a perfect snapshot of Alaska's wild beauty." Your pack can avoid those exact phrases and still mirror the cadence — "This is the day Alaska reveals itself" is corpus-marketing rhythm even without overlapping vocabulary.

Test while writing: if a sentence feels like it could appear on the cruise line's own marketing page (or in a third-party port guide that gets its language from the cruise line), rewrite. Replace with a specific, friction-bearing observation. Marketing voice telegraphs research-synthesis even when the words are different.

Local-Model Accents (Qwen / Gemma)

Everything above guards against general AI-slop and the Claude/GPT tells. A draft from a local model (Qwen, Gemma) carries its own accent. While writing or editing such a draft, also strip:

• The both-sides reflex (most important on vulnerable-audience pages). Local models reflexively soften an honest call by appending the opposite view — "however, it's worth considering…", "it's a balance between…", "some travelers may disagree." On a page whose job is a real verdict (is this accessible? is this worth the money?), that neutralizes the guidance the reader came for. This is not the conditional hedge ("may offer") already covered — it is a reflex to avoid taking a side. Make the honest call.
• Manufactured drama (Gemma). One-line contrast sentences and trailing ellipses ("And then the bill came…") to fake urgency. It mimics the native compressed chains ("Five decks. Five bars.") — but the real move reports; the fake one performs. Hold ellipses to at most one per page.
• Translationese (Qwen). Formal "dictionary" diction: utilize, manifestation, a multitude of, individuals. Use the word a traveler says: use, sign, a lot of, people.
• Self-correction leakage (Qwen). "Actually, to clarify…", "let me restate," "or rather" — reasoning residue. A published page has already decided. Cut.
• Numbered scaffolding (Qwen). "Firstly… Secondly…", "In terms of…", "When it comes to…" inside narrative prose. The page's headings carry the order; a real packing list is fine.
• Summary loops (Gemma). "In short… / Essentially…" restating the prior sentence. Say it once.

Full grep-able detection lives in voice-audit; these are the during-writing reflexes to catch first.

Native Moves (Protect These)

• First-person attestation with a date. "I sailed Allure in March 2024." "We tendered in Cabo last fall." Date the experience.
• Honest limitation. "I haven't been on the kids' deck." "I can't speak to suite class." Naming what you don't know is a trust move.
• From-the-pier specifics. What you see when you actually walk off. Not what the brochure claims is nearby.
• Real prices in real currency on a real date. "$32 in March 2024" beats "reasonably priced."
• Named real people. Crew first names, fellow passengers, family travelers. Not personas.
• Negative observations stated plainly. "The buffet at lunch was mediocre." Not "some travelers may find it underwhelming."
• Direct reader address for vulnerable moments. "If you're nervous about this, here's what to know." "You owe no one your story."
• Quiet confidence at the climax. "You will see whales." Short. Earned. No hedge.
• Logbook signoffs. Dated, named, brief.

Three Moves Worth Borrowing (Use Sparingly)

1. Voiced objection. State the reader's likely interruption in their voice, then answer it.
2. Cascade of three short questions. Three parallel questions before answers arrive. Once per page max.
3. Named-uncertainty illustration. "I'm not sure if it was the second or third night, but..." Naming uncertainty while telling the story anyway.

Rhythm and Cadence

The Building Pattern

The cruise voice has a specific rhythm: short declarative sentences that stack, then a longer sentence or a single phrase that lands.

Example:

The tender was rough. Twenty minutes, swells. We landed wet but laughing, and the dock crew already had towels stacked at the rail.

Example:

She cost more. She was worth it.

Every dollar.

This is not a rhythm trick. It's the way a person reports compression then release. When this pattern appears naturally, leave it alone. When it's being manufactured to sound like the author, cut it. The difference is felt, not measured.

Cadence Escalation

• Shrinking sentences at confidence moments. "You will see whales." "Worth it." "Every time." If the climactic moment has even-length sentences, it has been flattened.
• Two kinds of acceleration. Stripping conjunctions speeds up and strips to bone: "No tender. No bus. No way out." Stacking conjunctions slows down and adds weight: "She is the ship, and the home, and the platform." Both rhythms are yours. Protect both.
• Pause and pivot. After a peak observation, drop to a quieter sentence that pulls the reader close. "Then the engine cut. Just the water against the hull." If high moments roll straight into the next checklist item without the soft pivot, a native move has been lost.
• Anaphora at parallel beats. "Five decks. Five bars. Five different crowds."
• Em-dash for breath, not decoration. No more than two per paragraph.
• Paragraph-length variation — a one-sentence paragraph after a dense one is a feature, not a problem.
• One surprise word per page (not more).

Punctuation Fingerprint

The cruise voice uses:

• Em-dashes — sparingly, for genuine interruption or aside, not as all-purpose connectors. Cap: two per paragraph. If a passage has more, compress.
• Colons for announcement: "Here's what to know:"
• Periods for finality. Short sentences. Full stops.
• Commas for natural breath, not for listing everything the writer thought of.
• Semicolons rarely; only when two independent clauses genuinely lean on each other.

If a paragraph has more than two em-dashes, compress. Find the clause that's doing the interrupting and decide: does it earn its dash, or is it hiding in one?

The Controlled Flaw

AI never starts a sentence with "And." AI never uses a sentence fragment on purpose. AI never writes a paragraph that's just one word.

Human writers do all of these.

• Start a sentence with a conjunction when it creates forward motion: "And the dock crew was ready with towels." "But Allure had already cast off."
• Use intentional fragments at moments of emphasis: "Worth it." "Every time." "Not this trip."
• Leave a question hanging when the answer needs to arrive later, not immediately. Let two paragraphs of context sit between the question and its resolution.
• Allow a sentence that doesn't quite fit the paragraph — the thought that wandered in because the writer was thinking, not constructing.

These are not tricks. They are the natural movements of a mind reporting in real time, not executing a template.

Avoid

• Uniform sentence lengths
• Predictable paragraph rhythm (e.g., always 3-sentence paragraphs)
• Mechanical compression-release at every section

Pastoral Guardrails (For Vulnerable Audiences)

For accessibility, solo, and grief content the standard is heightened:

• Assume the reader is exhausted by being disbelieved or dismissed elsewhere. This is not another place that does that.
• Do not perform empathy. Report the practical, in clear language, with dignity intact.
• Do not treat the reader as a category. Treat them as a person who happens to be traveling with a specific situation.
• "Dignity-first" beats "inspirational." Always.
• The first paragraph must communicate someone thought about me. Within 15 seconds of arrival.

What Fails the Standard

• Uniform paragraph lengths
• Predictable section rhythm
• Symmetric structure across decks/ports/restaurants
• Smooth transitions masking weak moves
• Comfort arriving in the same paragraph as a real warning
• Generic "beautiful" or "vibrant" doing work that a specific should be doing
• Sustained absence of a real number, a real name, or a real date
• Performance of voice rather than the voice itself
• Promotional drift (the prose starts selling)
• Three or more consecutive sentences in identical grammatical shape
• One metaphor used three or more times across the page
• One observation restated multiple times without new evidence

The Safety Root Cause

All machine tells share one source: writing for safety instead of report. The diagnostic question is: Am I including this because the page needs it, or because I'm not sure the next sentence will land?

When in doubt, trust the specific. Cut the crutch. The reader feels the difference.

---

The PDFs are the cron job. The architecture is the mechanism. The voice is what the reader actually feels.

---

Version History

• v3.2.0 (2026-06-04) — Folded the v2.3.0 voice-audit findings into the during-writing companion. Four additions: (1) Section-Header Repetition Across Sibling Sections — mechanical template parallel across all parallel sections (every port day getting "Honest read on [port]") is an AI-shape tell; let each section's header be shaped by what the section contains. (2) Cross-Line / Cross-Ship Feature Integrity — venue names, brand partners, and class-generic features from sibling lines drift into prose as a training-data-echo signal (Mandara/Vitality, Observation Lounge/Two70, tender/dock — caught publicly on Anthem). When in doubt, look up the deck plan before writing. (3) Marketing-Rhythm Mirroring — packs can avoid quoting cruise-line marketing verbatim and still mirror its cadence ("This is the day Alaska reveals itself" maps to RC's "Sitka truly offers the best of Alaska"); read aloud, ask if it could appear on the cruise line's own marketing page. (4) Triplet-of-absences sub-rule under Rule of Three — capped at one per top-level document; subsequent instances need a concrete positive to anchor or restructure.
• v3.1.5 (2026-06-02, parallel branch later merged from main) — Added "Local-Model Accents (Qwen / Gemma)" under Plain Language Discipline: during-writing reflexes for the both-sides conviction-neutralizing reflex, Gemma manufactured drama, Qwen translationese, self-correction leakage, numbered scaffolding, and summary loops. Full grep detection lives in voice-audit. This work shipped on main as v3.2.0 (2026-06-02) but was merged into the branch alongside the parallel v3.2.0 work (2026-06-04) and renumbered to v3.1.5 for chronological clarity.
• v3.1.0 (2026-05-10) — Lifted ten sub-disciplines from Romans's like-a-human (in cruise voice): copula avoidance with replacement table, decorative adverb kill list, rule of three, low-probability details, dead metaphor, one-point dilution, syntactic template repetition, punctuation fingerprint, the controlled flaw, the building pattern with concrete examples, cadence escalation (two kinds of acceleration + pause-and-pivot). Reorganized Plain Language Discipline as the spine of the document.
• v3.0.0 — Initial cruise-voice version: hard-banned vocabulary, native moves, three borrowed moves, pastoral guardrails.