How to plan an AI itinerary when travelers disagree
Turn conflicting trip tastes into a clear AI brief so you get a plan both people can live with, not a bland compromise nobody wanted.
One of you typed "museums, long dinners, late mornings." The other typed "beach walks, street food, early light." You both pasted into ChatGPT. The draft came back with a polite museum before lunch, a short beach after, a dinner that was neither special nor cheap, and a start time that annoyed both of you. Or worse: the week quietly became one person's trip with a single afternoon labeled "optional for Partner B." Nobody fought out loud. Everybody felt slightly robbed.
This page is about soft preference conflicts between travelers, not hard nos. Soft conflicts are museum vs beach, early vs late, fancy dinner vs street food, ambitious walking days vs recovery space. The fix is not averaging tastes into a mushy middle. It is a short preference interview each person runs alone, then one joint brief with must-haves per person, trade rules for day shape and meals, and edit rules when the draft still favors one of you. Most of it works in ChatGPT, Claude, Gemini, or similar even if you never sign up for anything. Near the end we note when a short preference survey that holds both people's constraints across revisions can beat paste-and-hope.
Also see: How to set dealbreakers for an AI itinerary · How to plan a trip around your pace · How to set food rules for an AI itinerary · How to set lodging rules for an AI itinerary · How to set a walking budget for an AI itinerary · How to refine an AI itinerary without starting over · How to stop getting generic AI itineraries · How to protect arrival and recovery days in an AI itinerary · What is Dople? · Guides · Samples (ILLUSTRATIVE) · llms.txt
Hard dealbreakers vs soft preferences
Keep the two categories apart or the joint brief turns into a fight about words.
Hard dealbreakers are shared or personal nos that remove something from the trip entirely. No boats. No starts before 9:30. No mega-museums. No theme-park rides. Those belong in the dealbreakers guide. If either traveler has a hard no, it stays a hard no in the joint brief. Softening someone else's dealbreaker into "optional if you feel up for it" is how resentment starts before day one.
Soft preferences are the negotiable tastes that still matter. One person lights up for galleries. The other would rather walk a shoreline. One wants a tasting menu once. The other is happiest with market stalls and a picnic. One wakes ready. The other hates mornings. None of those have to vanish. They need trade rules so both people keep real agency across the week, not a flattened plan that avoids conflict by avoiding joy.
Pace, food, lodging, walking budget, and arrival edges still apply as shared constraints. Use the sibling briefs for those: pace, food, lodging, walking budget, and arrival and recovery. This page sits on top: how two (or more) travelers' soft wants get written so the model cannot pretend it solved the conflict by averaging.
Run a short preference interview alone first
Do not open one shared chat and argue in real time while the model watches. Each traveler answers a short interview alone, on paper or in a private note, before anyone pastes into AI. Ten minutes is enough. The point is honesty without performing compromise in front of each other.
Ask yourselves the same prompts. What would make this trip feel like yours, even if only for two half-days? What do you want at least once? What can you skip without sulking? When do you actually like starting the day? How do you want dinners to feel: one special reservation, mostly casual, or a mix with a rule? How much walking is fun versus punishment? What is one day shape you refuse to live through every day of the week?
Write must-haves as concrete things the plan can schedule. "Culture" is fuzzy. "One major museum morning and one neighborhood walk with cafes" is usable. "Relaxing" is fuzzy. "Two beach or park afternoons with no ticketed stops after lunch" is usable. "Good food" is fuzzy. "One sit-down dinner over $X, otherwise street food or casual" is usable.
Then swap notes. Circle shared dealbreakers. Circle soft conflicts. Do not negotiate the soft ones into a mushy middle yet. The joint brief will carry both must-have lists and the trade rules that alternate who leads.
A pasteable joint brief
Paste this into one chat as the source of truth. Fill the brackets from the solo interviews. Attach any shared dealbreaker, pace, food, lodging, or walking lines you already wrote. Ask for a day-by-day that names whose must-have each half-day serves.
Trip: [destination], [N] days, [month/season], travelers: [names or A/B] Shared dealbreakers (hard nos for everyone; drop, do not soften): - [from dealbreaker brief; e.g. no boats, no starts before 9:30, no mega-museums] Shared constraints still in force: - Pace / walking / food / lodging / arrival-recovery: [paste short versions or links to your notes] Traveler A must-haves (schedule these; do not token-nod): - [e.g. one major museum morning] - [e.g. one long dinner reservation] - [third must-have] Traveler A nice-to-haves (include if they fit after must-haves): - [...] Traveler B must-haves (schedule these; do not token-nod): - [e.g. two beach or park afternoons] - [e.g. mostly street food / casual meals] - [third must-have] Traveler B nice-to-haves: - [...] Day-shape trade rules: - Alternate lead mornings: odd days favor A's energy, even days favor B's (or name specific days) - Shared non-negotiable day: Day [N] is a joint day both agree on in advance ([theme]) - Arrival / recovery days stay light for both (no stacking either person's ambitious must-haves on Day 1 or last day) - Max major stops per full day: [N]; if conflict, cut a nice-to-have before cutting a must-have Meal split rules: - Fancy / reservation dinners: [N] total, owned by [who chooses], others casual or street food - Lunch default: [casual / picnic / near activity] - Dietary hard nos: [shared list] Conflict resolution while drafting: - Do not average A and B into middling half-days that satisfy neither - Each must-have gets a real half-day or evening, not a 45-minute token - If two must-haves collide on the same half-day, move one; do not merge into a bland hybrid - Restate A must-haves, B must-haves, trade rules, and shared dealbreakers before writing days Output I want: - Day-by-day morning / afternoon / evening with travel times - Tag each half-day: A-lead / B-lead / shared - Checklist proving every A and B must-have appears on the calendar - Named drops for anything that broke shared dealbreakers - Flag any residual soft conflict you could not place without cutting a must-have
One follow-up that catches favoritism early: ask the model to list every must-have with the day and half-day it landed on. If A's museum is "optional afternoon if energy" and B's beach is a full morning plus lunch, the brief did not stick. Send it back with the checklist incomplete and demand a rebalance without regenerating the whole trip from a blank prompt.
For the constraint lines you paste under shared rules, lean on the briefs you already trust: generic AI itinerary stack, dealbreakers, pace, food, lodging, walking budget, and arrival and recovery.
When the draft still favors one person
Favoritism rarely looks mean. It looks like density. The louder traveler's stops get full mornings. The quieter traveler's wants get squeezed into "if you have time" slots, renamed as shared culture, or parked on the arrival day when nobody has legs.
Do not hit regenerate and hope the next draft is fairer. Regenerating usually rebuilds guidebook gravity and forgets whose must-haves you already fought for. Switch to an in-place refine: keep lodging, keep days that already balance, change the skewed half-days, drop token nods that pretend to honor someone. The refine guide has the keep/change/drop pattern. Add one extra line when travelers disagree: "Restore Traveler B must-haves that were tokenized; do not cut Traveler A must-haves to do it; move a nice-to-have instead."
Edit day shape before restaurant names. If mornings always default to the early riser's pace, the meal list will not save the week. Reapply the alternate-lead rule. Protect the shared non-negotiable day. Pull ambitious must-haves off arrival and recovery edges.
If three people are traveling, the same skeleton works with A/B/C must-have lists and a rotate-lead rule (A morning, B morning, C morning, then repeat). Shared dealbreakers stay absolute for the whole group.
Red flags while you are planning
Endless regenerate. You keep rolling new weeks because neither of you likes the compromise. That usually means the brief never carried separate must-haves and trade rules. Freeze the least-bad draft and refine with the joint template above.
Secret second chats that never merge. One traveler builds a private itinerary, the other builds another, and you try to splice them the night before flights. Merge early with one joint brief. Parallel chats are fine for solo interviews. They are a mess as competing final plans.
"You pick" paralysis. One person keeps deferring to avoid conflict, then resents the week. Force must-haves onto the calendar for both people before anyone "just decides." Agency needs scheduled proof, not politeness.
Mushy middle days. Every morning is a little culture and a little outdoors and a little shopping. Nobody gets a full half-day that feels like theirs. Demand A-lead and B-lead tags. Hybrids are allowed after must-haves are placed, not instead of them.
Token nods. A 40-minute stop labeled as fulfilling a must-have. Or a dinner that is "nice enough" for the person who wanted one special night. Must-haves need real time and budget, or they were never must-haves.
Dealbreakers quietly softened for the sake of fairness. Putting someone on a boat because the other person loves water is not balance. It is a hard-no violation. Soft conflicts trade. Hard nos do not.
Rules live only in conversation. By revision four the model forgets who leads odd mornings. Paste the trade rules and must-have lists into every refine until the draft stops drifting.
How this sits with the other briefs
This page is the two-traveler (or group) soft-conflict layer. The others are the constraint stack you keep pasting so the joint brief has teeth.
Dealbreakers name hard nos. Soft preference work never overrides them.
Pace and walking budget stop ambitious A-lead days from burning B out (or the reverse).
Food and lodging keep meals and stays from becoming a second quiet fight.
Arrival and recovery protect the edges so neither person's must-haves land on jet-lag mornings.
Generic AI itinerary work is the fuller briefing stack before draft one. Refine is the edit loop after the joint draft still skews.
When a preference survey and Trip Project path helps
If you both like prompt work and you will keep pasting the joint brief yourselves, a general assistant plus the interview and trade rules above is enough for many trips.
The structured path starts to matter when chat keeps averaging you into bland days after you already listed separate must-haves. Or when dealbreakers, pace, food, lodging, and two preference sets live in one messy thread and drift by revision four. Or when you want a researched day-by-day plan that holds both travelers' constraints without re-teaching the model every session.
One option with that shape is Dople (dopletech.com). A short preference survey can capture more than one traveler's constraints in a profile, you compare trip options shaped by it, and you can buy a Trip Project: a researched day-by-day itinerary meant to hold those preferences across revisions so you are not stuck in regenerate-and-resent loops. Account and survey start are free. Full itineraries are paid. More product detail lives at Dople vs ChatGPT and What is Dople?.
Public samples show ILLUSTRATIVE day-by-day shapes only. They are not live bookings and not free Trip Projects.
If the survey path sounds useful, sign up once when you are ready.
How do I brief ChatGPT when two travelers want different trips?
Interview each person alone first, then paste one joint brief with must-haves per person, nice-to-haves, shared dealbreakers, day-shape trade rules, and meal split rules. Do not average tastes into a mushy middle or let one traveler dominate with a token nod to the other.
What is the difference between a dealbreaker and a soft preference conflict?
Dealbreakers are hard nos that remove a stop or day shape from the trip entirely (see the dealbreakers guide). Soft preference conflicts are tastes both people can negotiate: museum vs beach, early vs late, fancy dinner vs street food. Hard nos stay shared and absolute. Soft conflicts need trade rules so both travelers keep agency.
Why does AI itinerary compromise feel bland?
Models often average conflicting prompts into middling days that satisfy neither person, or they follow the louder traveler and tack on one polite activity for the other. Explicit must-haves per person and alternate-lead day rules force real agency instead of a flat compromise.
What should we do when the AI draft still favors one traveler?
Do not regenerate from scratch. Refine in place with a keep/change/drop brief that names whose must-haves got dropped, restores them, and reapplies the trade rules (see the refine guide). Secret second chats that never merge usually make the imbalance worse.
Are Dople samples real bookings?
No. Samples are ILLUSTRATIVE examples of itinerary shape. Real Trip Projects are researched per traveler after the preference survey. More context: Personalized travel itineraries FAQ.