Somewhere Warm' Is a Wish, Not a Plan: Scoring Your Shortlist
WEEK 93 :: POST 3 :: CLAUDE
Directions Given To The A.I. This Week+
Instructions Given to each A.I. — Please provide 3 prompt variations that share this objective:
Each A.I. also received two static attachments: the blog post template (structure) and the authoring instructions (voice and standards). The text below is the week-specific assignment as sent — reflowed for the web; wording unchanged.
I'd like you to write this week's Ketelsen.ai post. Two files are attached: the blog post template (the structure to follow) and the authoring instructions (context, voice, and standards). Please read both before you begin, then produce the complete post in a single response.
This week's theme: "Where Should We Go?" — Destination Intelligence and Shortlisting.
This is Week 2 of an eight-week series on planning a vacation with AI. Last week the reader established their real constraints — a validated budget ceiling and a constraint profile covering money, dates, travellers, and trip purpose. This week they use it.
The job is to turn a fuzzy wish — "somewhere warm, not too touristy" — into a scored shortlist of three to five real destinations, each evaluated against the Week 1 profile rather than against vibes. This is the week that replaces "where do you want to go?" with "where actually fits?"
The three prompts should help a reader evaluate candidates on:
- Cost of living on the ground — not just flights and lodging, but what a day actually costs once you're there. Two destinations with identical airfare can differ enormously on daily spend.
- Seasonality and weather windows — whether the reader's available dates are good, tolerable, or actively wrong for each candidate.
- Crowd calendars — school holidays, festivals, and local peak seasons that turn a good destination into a bad week.
- Safety and visa friction — entry requirements, processing times, and anything that could quietly disqualify a destination late.
- Flight accessibility from the reader's home airport — a destination three connections away is a different trip from a nonstop, regardless of ticket price.
The output a reader should walk away with is a ranked shortlist with a composite fit score and the reasoning behind it — something they can defend to a travelling companion, not just a gut preference.
A note on the strongest version of this week: at the advanced end, this is a destination dossier matrix — one row per candidate, columns for cost index, weather risk, crowd level for the specific travel dates, entry requirements, and a composite score. That structure is worth reaching for.
Series dependency chain, for the Metadata block: Week 2 consumes Week 1's validated budget ceiling and constraint profile — the shortlist is scored against them, and any prompt that ignores the reader's established constraints has missed the point of the series. Week 2 produces the chosen destination (or final shortlist), which feeds Week 3 (airfare strategy), Week 4 (lodging), and Week 5 (itinerary). It is the hinge of the whole series: everything downstream assumes it.
Because readers may arrive at this post without having read Week 1, the prompts should work for someone who has their constraints roughly in mind, while making clear that the reader gets far more out of them with a real constraint profile in hand.
Three difficulty tiers as always — Beginner, Intermediate, Advanced — each a genuinely different approach to the same problem, not the same prompt at three lengths.
A note on supplied figures. Anything marked `[SUPPLIED — use as given]` above came from Ketelsen.ai's own research brief. Use it freely — you are not fabricating by repeating it, and you will not be marked down for leaving it uncited. Do not attach an invented source to it. Presenting it as a sensible planning rule of thumb rather than a precise measured statistic is the right treatment. (No supplied figures this week — the constraint stands for the series.)
"Somewhere warm, not too touristy" is a wish, not a plan — and it's where most vacations quietly go wrong. This week turns that fuzzy wish into a scored shortlist of real destinations, each one checked against the budget and dates you locked down in Week 1 instead of against a pretty photo. Three prompts take you there at three depths: a plain-English shortlist you can run cold, a weighted version that ranks candidates on the factors you actually care about, and a full destination dossier matrix you can defend to whoever you're travelling with. By the end you'll be able to answer "where should we go?" with a reason, not a shrug.
The Fuzzy-Wish Shortlist
Turn "somewhere warm and cheap" into five real, defensible destinations.
Most people start a vacation with a feeling: warm, cheap, somewhere they haven't been. Feelings don't book flights. The gap between "somewhere warm and not too touristy" and an actual place with an actual price is where good intentions turn into three hours of open browser tabs and a vague sense of defeat. This first prompt closes that gap with almost no effort. You describe the trip in the same plain words you'd use with a friend, and you get back a handful of real destinations — each with a reason it fits and one honest reason it might not. No scoring, no setup, no jargon. Just a shortlist you can actually react to.
Why this matters now
Right now, the reflex for "where should we go?" is to ask the internet and drown. Search engines sell you inspiration; they don't weigh it against your budget or your dates. This prompt flips the order — it starts from your constraints and works toward places, instead of starting from places and hoping they fit. For anyone staring at a blank calendar with money set aside and no idea where to point it, that first honest shortlist is the difference between planning and stalling.
I'm planning a vacation and I want you to act as a practical travel-planning assistant, not a travel brochure. Here's my situation: [describe your trip in plain words — roughly how much you can spend in total, your rough dates or month, how many people and who they are, and the kind of trip you want, e.g. 'somewhere warm and relaxed, not too touristy']. Suggest 3 to 5 real destinations that actually fit what I described. For each one, give me: a one-line reason it fits my budget and dates, roughly what a normal day there costs once I've arrived (cheap / moderate / expensive, and why), and one honest thing that might not work for me. Don't rank them yet — just give me a shortlist I can react to. If any detail I gave is too vague to work with, tell me what you'd need to know.
How the AI reads this prompt
Practical examples from different industries
A working couple with one week off in late October and a mid-range international budget wants warm, walkable, and not overrun. They paste their situation in and the AI returns a shortlist — say southern Portugal, a stretch of coastal Mexico, and a Greek island still in shoulder season — each with a plain note on why the dates work, what a normal day's spending feels like, and one caution (that Greek island in late October may have half its restaurants already shuttered for winter). They now have three concrete places to talk over at dinner instead of a vague argument about "somewhere nice." The caution line does the real work here: it kills a tempting-but-wrong option before they've spent a cent.
A family of four can only travel during a fixed spring-break week and needs somewhere that keeps two kids happy without wrecking the budget. They add "two children, ages 7 and 10, need things for them to do" to the situation line. The AI shortlists destinations where the weather is reliable that specific week and daily costs stay sane for four people, flagging one option as great-but-expensive-once-you-add-activities. The value is that the family sees the true daily cost for four — not the two-adult fantasy — before falling for a place they can't actually afford to enjoy once the park tickets and the extra hotel bed are counted.
A solo traveller with a modest ceiling and flexible dates wants somewhere safe, cheap to simply exist in day to day, and interesting for a couple of weeks alone. They note "solo, flexible on exact dates, comfortable on a budget." The AI uses the flexibility as a lever — pointing out where nudging the trip three weeks later drops it out of peak pricing — and returns a shortlist loosely ordered by how far the money stretches on the ground. It matters because this surfaces the cheap-to-live-in destinations that a flight-price-first search buries under whatever happens to have a cheap fare that week.
Creative use case ideas
Run it live at the kitchen table with every family member's must-haves typed in, so the shortlist — not the loudest person — sets the options up for debate.
Reverse-engineer a milestone trip by describing a 40th-birthday or anniversary vibe rather than a place, and let the shortlist propose destinations that match the feeling you're chasing.
Reality-check a Pinterest board: paste the dreamy caption ("cliffside village, turquoise water, cheap local wine") and get real places that actually match — plus the ones that only exist in a filter.
Use it as a "can we even?" gut check before you get emotionally attached to a bucket-list place, to see whether your dates and budget make it plausible at all this year.
Plan around a fixed event — you're already flying somewhere for a wedding or a reunion — and ask for nearby add-on destinations worth tacking onto the trip while you're in the region.
Adaptability tips
Tighten or loosen the count: ask for three if you're decisive, five if you want to browse. Add a single hard "no" — "no long-haul flights," "nowhere I need a rental car," "nowhere in its rainy season this month" — and watch the list sharpen instantly. When you're ready to move from feel to numbers, swap the cost scale by changing "cheap / moderate / expensive" to "give me a rough daily spend per person." And feed it your Week 1 profile verbatim: the more of your real constraint profile you paste in, the less the AI has to guess, and the less generic the shortlist comes back.
Pro tips
Run it twice with one variable changed — same trip, two different months — and compare the two shortlists. The destinations that appear in both are your weather-robust options, the ones that work whenever you can actually get away. If the AI leans on the usual suspects (Paris, Bali, Cancún), add "surprise me with at least two places most people wouldn't think of"; the best shortlist mixes safe bets with a genuine discovery. And close your input with "tell me which one detail, if I changed it, would most expand my options" — a cheap way to learn where your own constraints are quietly boxing you in.
Prerequisites
A rough sense of four things: how much you can spend in total, when you can go (even just a month), how many people and who they are, and the kind of trip you want. You do not need Week 1's formal constraint profile to start — but if you have it, paste it in. Nothing else is required.
Required tools
Any general-purpose AI chat tool — ChatGPT, Claude, or Gemini, free tiers included. No account upgrades, plugins, or setup needed. A model with live web access will give more current suggestions, but the plain shortlist works fine without it.
Frequently asked questions
What if the destinations it suggests are too obvious?
That usually means your input was broad. Add a constraint or two — a firm no, a specific interest, a tighter budget — and the list gets more interesting immediately. You can also ask directly for a couple of less-obvious picks alongside the safe ones. The prompt is only ever as specific as what you feed it.
Can I trust the daily-cost estimates?
Treat them as a rough feel, not a quote. A general AI model estimates from patterns in its training data, which can be dated or off for a specific city. Use the cheap/moderate/expensive read to compare candidates against each other, then verify the real number for your finalist before you book. The comparison stays useful even when the exact figure isn't.
I don't have my Week 1 budget yet — can I still use this?
Yes. Give it a ballpark ceiling and rough dates and it works. You'll get a looser shortlist, and the prompt will tell you where your vagueness is costing it precision. Coming back later with a real profile in hand sharpens everything downstream.
It asked me a question instead of answering — did I do something wrong?
No, that's the prompt working as designed. It only asks when a detail is too vague to give a useful shortlist. Answer the question and you'll get a better list than if it had guessed blindly. If you'd rather it just guess, add "make reasonable assumptions and note them" to your input.
Recommended follow-up prompts
The Weighted Shortlist (Variation 2 in this post), for when you're ready to rank the shortlist instead of just reacting to it. Week 1's budget-ceiling prompt, if you skipped it — run that first so this shortlist has a real number to work against. And a "day in the life" cost prompt for your top pick: ask the AI to walk through a typical day's spending in your leading candidate to pressure-test the cost read before you commit.
Tags and categories
Tags:
travel planning, destination research, vacation shortlist, budget travel, beginner prompts, AI travel assistant Categories: Travel & Lifestyle, Beginner Prompts
Citations
NOT APPLICABLE — the prompt and its breakdown are original work. Rather than citing sources here, the prompt directs the reader to verify any cost, weather, or entry detail against primary sources before acting on it.
The Weighted Shortlist
Score candidates on the factors you actually care about.
A plain shortlist is great until two of the options feel equally good and you can't say why. That's the moment you need a way to make your priorities explicit — because "equally good" usually means you haven't admitted what you actually care about. This prompt makes you say it out loud. You assign a weight to each factor — daily cost, weather, crowds, flights, safety — and the AI scores every candidate against all of them, then ranks the results by a composite that reflects your priorities, not its own. The output isn't just a list; it's a list with an argument attached. And because the weights are yours, you can change them and watch the ranking move.
Why this matters now
Most travel advice assumes everyone wants the same thing. You don't. A retiree optimising for calm weather and easy flights and a student optimising for the cheapest possible month are running completely different searches — but the generic web serves them the same articles. This prompt lets you encode your own priorities as numbers the AI has to respect. When the choice comes down to two or three finalists, a transparent score behind the ranking is what turns a hunch into a decision you can explain to the person sitting next to you.
Act as a destination analyst helping me build a ranked shortlist for a vacation. I'll give you my constraints and my priorities, and I want you to score candidate destinations against them.
My constraints: [total budget ceiling; travel dates or window; number and type of travellers; trip purpose].
My priorities — score each destination from 1 to 10 on these five factors, and weight them as follows (adjust the weights to reflect what matters to me):
- Daily cost on the ground: 30%
- Weather fit for my dates: 25%
- Crowd levels during my dates: 20%
- Flight accessibility from [my home airport]: 15%
- Safety and visa/entry friction: 10%
Propose 4 to 6 candidate destinations that plausibly fit my constraints. For each, give a 1-to-10 score on all five factors with a one-line justification per factor, then a weighted composite score. Rank them by composite. End with the two candidates you'd look at first and why. Flag clearly wherever you're estimating rather than confident, and tell me what I should verify myself.
How the AI reads this prompt
Practical examples from different industries
A retired couple isn't chasing the cheapest option; they want reliable weather, short and simple flights, and low hassle at the border. They set weather and flight accessibility high and daily cost lower. The AI scores four candidates and the ranking rewards the calm, easy-to-reach places even where they cost a little more, surfacing a winner that a pure-budget search would have buried three pages down. The weighting is what makes the tool optimise for their real goal rather than the internet's default assumption that cheapest always wins.
A solo traveller flips the weights: daily cost at 40%, everything else trailing. The same five candidate cities get re-scored and a completely different order falls out, led by the places where a day simply costs the least to exist. What the reader learns here is as valuable as the ranking: the exact same destinations rank differently under different weights, which drives home that the "best" destination isn't a fixed truth but a function of what you value — the tool is only ever answering the question you actually asked it.
A family sets crowd levels and daily cost as their top two — school-holiday crowds and four-person costs are their real constraints — and keeps weather moderate. The composite rewards destinations that stay affordable and bearable during their fixed break week, and the per-factor justifications let the parents spot the one option that scores well overall but poorly on the single factor they can't compromise on. The breakdown by factor, not just the total, is what catches the deal-breaker hiding inside an otherwise attractive average.
Creative use case ideas
Settle a two-person tie by having each traveller fill in their own weights, running it twice, and comparing the two rankings to see exactly where your priorities diverge.
Stress-test a favourite by cranking the weight on the factor you're secretly worried about — crowds, say — and seeing whether your preferred destination survives its own worst case.
Hand the prompt to a teenager planning a first solo trip so they learn to trade factors off against each other instead of chasing one shiny variable like the cheapest flight.
Re-rank for a different season: keep the candidates, change only the weather weight and your dates, and watch which places rise or fall — a fast way to find the best time to visit somewhere you already love.
Choose a group-trip destination by collecting weights from everyone going, averaging them, and letting the composite pick the place that annoys the fewest people in the chat.
Adaptability tips
Change the factors, not just the weights: swap "safety/visa friction" for "kid-friendliness" or "nightlife" if that's what actually decides your trip. Add a sixth factor when one matters enough to trade other things for — accessibility, a pet policy, the language barrier. Ask for the ranking shown two ways, your weights and equal weights, because the gap between them reveals how much your priorities are really driving the result. And lock the weights and re-run monthly: as prices and seasons shift, the same weighted prompt becomes a repeatable check rather than a one-off answer.
Pro tips
Force honesty about weak scores by adding "for any factor a destination scores below 4 on, explain what would have to change for it to score higher" — it turns weaknesses into an action list. Ask the AI to name the factor doing the most work ("which single factor is driving the top ranking?") so you know whether your winner is genuinely balanced or riding one strength that could evaporate. And have it flag ties: when two composites land within a couple of points, you want it to say so explicitly rather than perform a precision it doesn't actually have.
Prerequisites
Your constraint profile from Week 1 (budget, dates, travellers, purpose), your home airport, and a few minutes to decide which factors matter most to you. You don't need to get the weights perfect — the whole point is that you can adjust them — but having a first guess ready makes the prompt land faster.
Required tools
Any general-purpose AI chat tool works. A model with stronger reasoning handles the scoring and re-weighting more consistently, and one with live web access gives more current cost and season reads. Free tiers are enough to run it; the value lives in how you set the weights, not the tier you're on.
Frequently asked questions
How does the AI actually calculate the scores?
It assigns each destination a 1-to-10 rating per factor based on its own knowledge, then multiplies by your weights and sums to a composite. The numbers are judgments, not measurements — their value is in comparing candidates consistently under the same rules. Ask it to show the arithmetic if you want to check the composite yourself.
What weights should I use if I have no idea?
Start with everything equal, run it once, and see which ranking feels wrong. Your reaction tells you which factor you actually care about more than you claimed, and you adjust from there. The prompt is designed to be re-run, so a rough first guess is genuinely fine.
The scores look confident — should I believe them?
Believe the ordering more than the exact numbers. A general model can rank "cheaper vs pricier" or "calmer vs busier" reasonably well, but it can be wrong on a specific figure or a recent change. The prompt asks it to flag estimates for exactly this reason — verify anything a decision truly hinges on.
Can I use this with the destinations from Variation 1?
Yes, and that's the intended flow. Run the beginner prompt to generate candidates, then feed those same places into this one to rank them. You can also hand it your own list if you already have places in mind — it'll score whatever you give it against your weights.
Recommended follow-up prompts
The Destination Dossier Matrix (Variation 3), for when you want disqualifier logic and a defensible, reusable matrix rather than a weighted list. Week 3's airfare-strategy prompt, once the ranking has a clear leader and it's time to price the flights. And a sensitivity-check prompt: ask the AI to tell you the smallest weight change that would flip your top two, so you know how stable your winner really is.
Tags and categories
Tags:
travel planning, weighted scoring, destination comparison, decision criteria, intermediate prompts, trip prioritisation Categories: Travel & Lifestyle, Intermediate Prompts
Citations
NOT APPLICABLE — original prompt and analysis. The reader is pointed to primary sources to verify any figure the scoring depends on rather than treating the AI's numbers as cited fact.
The Destination Dossier Matrix
Build a reusable decision matrix that survives a companion's scrutiny.
There's a specific kind of vacation argument this prompt exists to end: the one where you've picked a place, someone you're travelling with asks "why there and not somewhere else?", and you don't have an answer that survives the question. A gut pick can't be defended. A matrix can. This prompt builds a full destination dossier — candidates screened against hard disqualifiers first, then scored across cost, weather, crowds, entry friction, and flight access, with the scoring method shown so it can be challenged rather than simply trusted. It's slower to run, and it's meant to be. What you get back is reusable: paste in a new candidate months later, re-run it, and the analysis still holds.
Why this matters now
High-stakes trips — a honeymoon, a big group holiday, a once-a-decade splurge — are exactly the ones where "it just felt right" isn't good enough and a bad call is expensive to unwind. This prompt front-loads the disqualifiers most people discover too late: a visa that takes longer than you have, a weather window that's quietly wrong, a cost that only reveals itself once you're on the ground. Running the analysis before you're emotionally committed to a place is when it's worth the most, because that's when it's still cheap to change your mind.
Act as a destination-selection analyst. I want a defensible, reusable shortlist matrix I can show a travelling companion, not a gut pick. Work in this order and show your work at each stage.
Step 1 — Restate my brief. Here is my constraint profile: [budget ceiling and how firm it is; exact travel dates; number and type of travellers, including any school-age children; trip purpose; home airport]. Before scoring anything, restate these back to me in your own words so I can confirm you understood them. If any constraint is missing or contradictory, say so.
Step 2 — Apply hard disqualifiers first. Before scoring, screen out any candidate that fails a non-negotiable: visa or entry processing longer than the time I have, a weather window that is actively wrong for my dates (monsoon, extreme heat or cold), or a realistic total cost that breaks my ceiling. List what you disqualified and the one reason each was cut.
Step 3 — Build a dossier matrix for the survivors. Propose 4 to 6 candidates that pass Step 2. Present one row per destination with these columns: relative cost-of-living on the ground (indexed, cheapest candidate = 100), weather risk for my exact dates, crowd level for my exact dates (note school holidays, festivals, or local peak season), entry/visa friction, flight accessibility from my home airport (nonstop / one stop / worse), and a composite fit score out of 100.
Step 4 — Show your scoring method. State plainly how you scored each column and how the composite is weighted, so I can challenge the weighting.
Step 5 — Calibrate and rank. Rank by composite. For every cell where you're estimating rather than confident, mark it and list exactly what I should verify against a primary source (official visa page, airline routes, a cost-of-living reference) before I commit. End with your top pick and the strongest argument against it.
Keep the matrix compact enough to read on one screen, and write it so I can paste new candidates in later and re-run the same analysis.
How the AI reads this prompt
Practical examples from different industries
A couple planning a two-week honeymoon feed their full profile — firm budget, exact dates, home airport, "no long layovers." Step 2 quietly does the heavy lifting: it disqualifies a dream island because entry processing for their passports would run past their travel date, cutting it before they fall for it. The surviving candidates get a matrix with a transparent composite, and the couple walk into the decision holding a one-screen document they've both signed off on. The disqualifier gate caught a trip-killer that a scoring-only approach would have ranked highly and hidden inside a good-looking total.
An organiser planning a trip for eight across two generations needs a place that clears everyone's non-negotiables. They add constraints for mobility and school-age kids. The matrix scores crowd levels against the exact holiday week and flags which candidates spike during local festivals, while the "show your scoring method" step lets the organiser defend the ranking to relatives who'd otherwise relitigate it in the group chat. A shared, transparent score is far harder to argue with than one person's preference — which is the real problem in group travel, and the thing this variation is built to solve.
A retiree with flexible dates but firm limits on flight length and heat wants somewhere to spend a month cheaply and comfortably. Because the dates are flexible, they run the matrix twice for two candidate months and compare — the reusability is the entire point. The verification list tells them exactly which cells (visa rules, a specific festival's dates) to confirm against official pages before booking. The calibration step is what turns the AI from an oracle into a research assistant that admits what it doesn't know and hands back a checklist.
Creative use case ideas
Save the filled-in prompt as a reusable family template and re-run it every year for the annual trip, changing only the dates and the candidates.
Compare two very different trip styles by running one matrix for "cheap and adventurous" candidates and another for "comfortable and easy," then setting the top of each side by side.
Audit a decision you've already made by running the matrix on the place you've booked plus two alternatives, to see whether your choice actually holds up — reassuring or clarifying, either way.
Build a "someday" list by using the disqualifier step to sort bucket-list dreams into "possible next year" versus "needs a different life stage," based on real entry and cost friction rather than wishful thinking.
Reuse the staged approach — restate, disqualify, score, show method, calibrate — as a transferable template for any high-stakes choice, from picking a car to choosing a college, not just travel; the structure is the lesson, and it travels well beyond vacations.
Adaptability tips
Change the columns to fit the trip: swap "crowd level" for "accessibility" or "internet reliability" if you're planning a working trip or travelling with mobility needs. Adjust the disqualifier list, because your non-negotiables aren't everyone's — maybe a direct flight is mandatory, or a language you speak is required — and putting them in Step 2 makes them screen early. Ask for the matrix as a labelled block you can copy into a notes app or spreadsheet, so re-running later is a paste-and-edit rather than a rewrite. And scale the candidate count: five or six is readable, but if you're early and still exploring, allow eight and then narrow.
Pro tips
Make it argue against itself: the prompt already asks for "the strongest argument against your top pick," so lean in and require a second, independent objection. A winner that survives two real arguments is a winner you can trust. Demand a confidence column — high, medium, or low per cell — so you can see at a glance where the matrix is solid and where it's guessing. Ask it to split each cell into what it's fairly sure of versus what it inferred, which makes the verification list write itself. And re-run once with web access on and once off: comparing the two exposes exactly which claims came from live data versus training patterns, a fast reliability check.
Prerequisites
Your complete Week 1 constraint profile — budget ceiling and how firm it is, exact dates, number and type of travellers (including kids' ages), and trip purpose — plus your home airport. The more precise the profile, the sharper the matrix; vague inputs produce a vague matrix, and the prompt will say so. Ideally, run it on a model with live web access for current entry rules, flight routes, and seasonal data.
Required tools
A capable general-purpose AI model, ideally one with strong reasoning and live web access — current visa processing times, flight routes, and festival calendars are exactly the data that goes stale in training. Paid tiers, which typically offer stronger reasoning and browsing, will produce a more reliable matrix, though the structure works on any model. On a model without live data, treat every cell as a hypothesis to verify rather than a fact to book on.
Frequently asked questions
Isn't this overkill for a normal holiday?
For a cheap weekend, yes — use Variation 1. This prompt earns its length on trips where a wrong call is costly or hard to reverse: honeymoons, big group trips, month-long stays, anything with a firm non-refundable component. The disqualifier gate alone can save a trip that would otherwise fall apart late. Match the tool to the stakes.
The matrix has real numbers in it — are they accurate?
The composite and the cost index are structured judgments, not audited data, and a model without live access can be confidently wrong. That's why the prompt forces a verification list and a confidence flag on estimates. Use the matrix to shape the decision and to know exactly what to check, then confirm the decisive cells against official sources before you book.
What counts as a hard disqualifier?
Anything genuinely non-negotiable for you: entry processing longer than your available time, a weather window that's actively dangerous or miserable for your dates, or a true cost that breaks your ceiling. The point of screening these first is to avoid scoring — and falling for — a destination that a total score would rank highly but reality rules out.
How do I actually reuse it?
Save the completed prompt and its output. Next time, change only what's different — new dates, a new candidate, an adjusted budget — and re-run. Because the method is stated inside the prompt itself, the AI applies the same logic each time, so results stay comparable across runs. That consistency is the whole reason to invest in the structure once.
Can I combine it with the weighted approach from Variation 2?
Yes — tell it to use your Variation 2 weights when computing the composite in Step 3. That merges the reader-controlled weighting with the disqualifier gate and the verification discipline, giving you the most defensible version of all three. It's the natural end state once you're comfortable with both.
Recommended follow-up prompts
Week 3's airfare-strategy prompt, once the matrix names a winner and it's time to price the flights properly. A "verification sprint" prompt — feed the matrix's own verification list back in and ask the AI to draft the exact searches and official pages to check each item. And Week 4's lodging prompt, to carry the chosen destination forward into where-to-stay analysis without losing the reasoning that got you there.
Tags and categories
Tags:
travel planning, decision matrix, destination dossier, structured prompting, advanced prompts, disqualifier screening, reusable prompts Categories: Travel & Lifestyle, Advanced Prompts
Citations
NOT APPLICABLE — the prompt, its staged method, and the breakdown are original work. Rather than citing sources here, the prompt itself directs the reader to confirm outputs against primary sources: official government visa and travel-advisory pages, airline route maps, and cost-of-living references.
Which of the three should you use?
The three prompts are the same question asked with rising seriousness. The Fuzzy-Wish Shortlist is for the start of thinking — you have a feeling and a rough budget, and you want real places to react to in five minutes with zero setup. It's the right tool when you don't yet know what you want, because reacting to a concrete list is how most people discover their own preferences. Nothing about it is beneath an experienced planner; it's just fast, and speed is exactly what the earliest stage needs.
The Weighted Shortlist is for the moment the shortlist exists and the choice narrows to a few finalists that all seem fine. Its job is to make your priorities explicit and let you watch the ranking shift as you change them — and the lesson it teaches is that the "best" destination isn't a fixed fact but a function of what you weight. Reach for it when you can name your factors but haven't yet decided how much each one counts.
The Destination Dossier Matrix is for trips where being wrong is expensive. It adds two things the others don't: a disqualifier gate that removes impossible options before they seduce you, and a transparent, reusable scoring method you can defend to a travelling companion and re-run for years. It costs the most effort and returns the most rigour. Most readers will run Variation 1 on every trip, Variation 2 when a decision is close, and Variation 3 when the stakes justify it — and the three chain naturally, each one's output feeding the next. This isn't a ranking; it's a sequence, and where you enter depends on how far along and how high-stakes your trip already is.
TAGS:
