Fitting the Wish-List Into One Week Without Losing Your Mind
WEEK 96 :: POST 1 :: GOOGLE GEMINI
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: "Building the Itinerary That Doesn't Break" — Day-by-Day Design and Pacing.
This is Week 5 of an eight-week series on planning a vacation with AI. By now the reader has a budget ceiling (Week 1), a destination (Week 2), booked flights that fix the dates and arrival time (Week 3), and a place to stay whose location is now known (Week 4). This week they turn a list of things they want to do into a day-by-day plan that survives contact with a real trip.
Most itineraries fail the same three ways, and none of them are about picking the wrong attractions. They fail from over-scheduling — cramming a day so full that one late lunch collapses everything after it; from geographic ping-ponging — crossing the city four times because the plan was built by interest rather than by map; and from ignoring the calendar — arriving to find the museum closed on Mondays and the one restaurant they cared about booked out for three weeks. The job this week is a plan built around how days actually go, not how they look on paper.
The deliverable the reader should walk away holding is a day-by-day itinerary they can defend: activities clustered so each day stays in one part of the map, a realistic pace, a booking-deadline calendar sorted by how far ahead each thing must be reserved, and a backup for the days most likely to fall apart.
The three prompts should help a reader work through:
- Clustering by geography, not by interest. Grouping the things they want to do by where they are, so a day moves through one neighbourhood or district instead of doubling back across town. The AI is good at taking a list of places plus the reader's lodging location and proposing sensible clusters — as long as the reader supplies the places and the rough map.
- Pacing with an anchor-and-flex rhythm. One committed thing per day — the anchor — with everything else held loosely as optional. This is the antidote to over-scheduling: a day with a single non-negotiable and a menu of maybes bends instead of breaking when something runs long. Building in a deliberate zero day — a day with nothing planned — belongs here too.
- Reservation lead-time intelligence. Which kinds of things book out far in advance and which can be decided the morning of, turned into a calendar sorted by book-by date so nothing is lost to a deadline the reader never saw. The AI supplies the pattern — that certain restaurants, timed-entry museums, and marquee experiences typically need booking well ahead — while the reader confirms the actual dates against live booking pages.
At the advanced tier, the strongest version of this week is a structured day-by-day plan with pacing rules made explicit: each day an anchor plus ranked optionals, transit time between clustered stops accounted for, a backup option per day, and a reservations-deadline calendar the reader can act on. That is the structure worth reaching for.
A hard constraint, carried forward from Weeks 3 and 4 and just as binding here. AI models cannot see live opening hours, this season's closure days, current reservation availability, or today's transit schedules — and their recall of a specific venue's hours is stale and frequently wrong. No prompt in this post may ask the AI to state a specific attraction's opening hours, claim a particular restaurant is bookable on a given date, or assert current transit times as fact. A confidently wrong opening time sends the reader across the city to a locked door. Prompts should have the AI produce what to verify and where — the questions to ask, the pages to check, the buffers to leave — rather than deliver a schedule stated as certain.
Design the prompts so the AI does what it is genuinely good at: organising a messy wish-list into a coherent map-aware sequence, enforcing a sane pace, and naming what must be booked ahead. The reader supplies the wish-list, the lodging location, and the confirmed hours; the AI supplies the structure and the sequencing. Posts that have the AI invent hours or availability should expect to be marked down on Practical Utility, exactly as in Weeks 3 and 4.
Series dependency chain, for the Metadata block: Week 5 consumes the booked lodging and its location from Week 4 (the itinerary is built outward from where the reader wakes up each morning), the confirmed dates from Week 3, the destination from Week 2, and the budget ceiling from Week 1. Week 5 produces the day-by-day plan and its reservation calendar, which Week 6's logistics-and-protection audit and Week 7's in-trip prompts both assume as the shape of the trip they are protecting and running.
Because readers may arrive at this post without having read Weeks 1 to 4, the prompts should work for someone who knows their destination, dates, lodging area, and a rough list of what they want to do, while making clear they get far more from them with a real constraint profile and confirmed bookings 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.
On examples: this is a consumer travel topic. The template lists tech startup / retail / freelance as suggested industry examples — those are marked MAY, and this week you should almost certainly adapt them. Families pacing a trip around nap times and young children, couples balancing one person's museum day against the other's beach day, a group trying to share a plan without a dozen group-chat threads, and older travellers for whom walking distance between stops decides the day are the right contexts here. Choosing them over the suggested business examples is correct behaviour and will not be scored against you.
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. (No supplied figures this week. Given the live-hours-and-availability constraint above, this is a bad week to invent any — if you find yourself reaching for a venue's opening hours or how far ahead a restaurant books, that is the signal to restructure the prompt so the reader supplies the real detail instead.)
## BEFORE YOU SUBMIT — STRUCTURAL CHECK
(This block is identical every week. It exists because these specific items are the ones posts drop, and a dropped structural item costs compliance points for something that takes one minute to add.)
Your post is parsed by a script before any human reads it. Confirm all seven:
1. ☐ Response begins with `PLATFORM: <your name>` and `WEEK: 5` 2. ☐ `## Lead` present once, at the very top, before Variation 1 3. ☐ `## In one line` present in all three variations 4. ☐ `## What this prompt gives you` present in all three variations 5. ☐ `## The Prompt` present in all three variations, with the prompt in double quotes beneath it 6. ☐ `## Introductory Hook` and `## Current Use` present in all three variations (three of each — not one) 7. ☐ Every template heading written as `##`, none bolded instead; prompt breakdown is running text split on ` : `, with no `###` headings inside it
A complete post has 57 `##` headings. If your count is well short, a section is missing or was bolded instead of hashed.
One extra check this week: confirm no prompt asks the AI to state a specific venue's opening hours, closure days, or current reservation availability, or to present a transit time as fact. Those must be things the reader goes and verifies.
You have a destination, a budget, confirmed flights, and a place to sleep—now you have to figure out how to fit your entire wish-list into a single week without losing your mind. Most itineraries fail not from bad choices, but from over-scheduling, geographic ping-ponging, and showing up to find a museum locked or a restaurant fully booked. This week provides three prompts at three depths to solve this: a beginner prompt for grouping stops by neighborhood, an intermediate prompt to establish a flexible daily rhythm, and an advanced prompt that builds a comprehensive day-by-day plan with a reservation deadline calendar. Let’s build a schedule that actually survives contact with reality.
The Neighborhood Cluster Map
Group your wish-list by location to stop crossing the city twice.
When we plan trips, we naturally list things by how much we want to see them. The problem is that enthusiasm has no sense of geography. If you follow an interest-based list in order, you will spend half your vacation in transit, bouncing from the north side of the city to the south and back again. This beginner variation takes your messy wish-list and your hotel's location, and groups everything into logical geographic clusters.
Why this matters now
Travelers waste hours of their hard-earned vacation time stuck in transit simply because they didn't look at a map before leaving the hotel. By letting AI handle the spatial reasoning right now, you immediately identify which attractions belong on the same day. It prevents the exhaustion of geographic ping-ponging and makes your days infinitely more walkable and relaxed.
I am traveling to \[Destination\] and staying in the \[Neighborhood/Area\] neighborhood. I have a list of things I want to do, but I don't know where they are in relation to each other. Please group the following wish-list into geographic clusters, so that items in the same cluster can reasonably be visited on the same day. Do not invent or estimate transit times or state any opening hours, as I know AI cannot see live data. Instead, for each cluster, give me a 'To Verify' checklist of the transit routes I need to look up and the venue hours I need to confirm. Here is my wish-list: \[Insert List\]
How the AI reads this prompt
Practical examples from different industries
Family Vacationers:
A family traveling to Washington D.C. inputs a list containing the zoo, five different museums, and three monuments. The AI outputs clusters, grouping the Air and Space Museum with the Capitol building, and the Zoo on its own separate day, providing a checklist to verify Metro line disruptions and timed-entry pass requirements. This prevents parents from dragging exhausted toddlers across the National Mall four times in one day. Solo Backpackers: A solo traveler in Tokyo staying in Shinjuku inputs a sprawling list of temples, cafes, and shopping districts. The AI clusters Harajuku, Shibuya, and Shinjuku together for the west side, and Asakusa and Akihabara for the east side. The output prompts the traveler to verify the last train times for the east-side cluster, preventing an expensive midnight taxi ride. Couples Retreats: A couple visiting Paris has a mix of romantic dinner spots, major art galleries, and small boutique shops on their list. The AI clusters a morning at the Louvre with an afternoon wandering Le Marais, keeping the pace leisurely. It provides a reminder to check which days the specific galleries are closed, as Parisian museums have notoriously staggered closure days.
Creative use case ideas
- Photography Expeditions: Grouping shooting locations by neighborhood to maximize the golden hour light without spending it on a subway.
- Food Tours: Clustering bakeries, cafes, and restaurants by district so you can eat your way through a neighborhood logically.
- Hobbyist Meetups: For someone visiting a city for a niche hobby (like visiting multiple yarn stores or record shops), grouping them geographically to optimize the shopping day.
Adaptability tips
You can easily adapt this prompt by adding constraints like, "I can only walk 2 miles a day" or "I am relying entirely on public buses." This forces the AI to consider the density of the clusters it creates, making the output more tailored to your mobility.
Pro tips
Ask the AI to identify any "outliers" on your list—places that are geographically stranded far away from everything else. This helps you decide if that one specific attraction is actually worth a half-day detour.
Prerequisites
You need a confirmed destination, the neighborhood of your lodging, and a rough brainstormed list of things you want to see and do.
Required tools
Any standard generative AI (ChatGPT, Claude, Gemini). No specialized plugins required.
Frequently asked questions
Why won't the AI just tell me the transit times?
Generative AI models are trained on past data, not live transit APIs. Bus routes change, trains get delayed, and weekend schedules differ from weekdays. If the AI guesses, it might strand you. It's always safer to check a live map app. What if my list is too long for the amount of days I have? The AI will still cluster them geographically, but the clusters might be massive. If you see a cluster with ten items, you will need to use your own judgment to edit it down or split it into two days. Does it matter what neighborhood I'm staying in? Absolutely. Your starting point dictates the flow of the entire day. A cluster that works beautifully for someone staying downtown might be a logistical nightmare for someone staying in the outer suburbs.
Recommended follow-up prompts
"Look at Cluster 1 and tell me if it contains mostly indoor or outdoor activities, so I can match it to the weather." "Identify any natural 'rest stops' (like major parks) within this geographic cluster."
Tags and categories
Tags:
vacation planning, geography, clustering, travel logistics, itinerary Categories: Travel & Lifestyle, Organization
Citations
NOT APPLICABLE
The Anchor-and-Flex Pacer
Build a stress-free schedule with one non-negotiable anchor daily.
The fastest way to ruin a vacation is by treating it like a military operation. When you schedule every hour of the day, a single long lunch or a delayed train causes a domino effect that collapses the rest of the afternoon. The secret to a trip that feels like an actual break is the "anchor-and-flex" method. This intermediate prompt builds your day around one non-negotiable anchor activity, keeping the rest of your wishlist loosely held as optional modules that can bend when the day runs long.
Why this matters now
Travelers are increasingly burning out on their own vacations. By implementing a pacing strategy right now, you protect your future self from exhaustion. This prompt explicitly limits how much you commit to, ensuring you actually enjoy the things you do see, rather than sprinting through them just to check a box.
I am planning a vacation to \[Destination\] for \[Number\] days. I have my wishlist clustered by neighborhood, but I tend to over-schedule. Help me pace this trip using the 'anchor-and-flex' method. For each day, give me exactly ONE 'Anchor' activity (the non-negotiable core of the day) and 2-3 'Flex' activities (optional things nearby that I can do if I have time and energy). Please also designate one day as a 'Zero Day' with absolutely nothing scheduled. Do not state specific venue opening hours or transit times; instead, provide a 'Verification Checklist' for each day noting what I need to look up on the venues' official websites.
How the AI reads this prompt
Practical examples from different industries
Parents of Young Children:
A family inputs their list for a theme park destination. The AI selects the main park as the Anchor for Tuesday, with the hotel pool and a nearby themed diner as Flex options. It leaves Thursday as a Zero Day. This prevents meltdowns by acknowledging that a toddler cannot do three parks in three days. The verification checklist reminds the parents to check the park's live stroller-rental availability. Accessibility-Conscious Travelers: An older traveler inputs a list for Rome. The AI selects the Vatican as the single Anchor for the day, providing nearby cafes as low-energy Flex options. This ensures the traveler has a fulfilling day without pushing beyond their physical limits. The checklist reminds them to verify elevator access and skip-the-line ticket requirements. Group Trips: A bachelorette party of eight people uses this to balance the schedule. The AI makes the afternoon boat tour the Anchor, leaving the morning as a Flex period where early risers can get coffee and late sleepers can rest. This stops the endless group-chat arguments about when everyone needs to be ready, providing a single mandatory meeting point.
Creative use case ideas
- Convention Attendees: Balancing mandatory conference keynotes (Anchors) with optional networking events or local sightseeing (Flex).
- Sports Tournaments: Traveling for a weekend tournament where the games are Anchors, and nearby restaurants or quick sights are Flexes depending on when the games end.
- Remote Workers (Workcation): Using focus blocks as Anchors and local exploration as Flex options based on daily energy levels.
Adaptability tips
You can tweak the ratio based on your travel style. If you are highly energetic, you can ask for "Two Anchors (one morning, one evening) and two Flexes." If you are recovering from burnout, you can ask for "One Anchor every other day."
Pro tips
Ask the AI to identify which of your Flex activities could easily be moved to your Zero Day if you suddenly find yourself bored and wanting something to do.
Prerequisites
You must know how many days you are traveling and have a rough idea of what you want to do (ideally geographically clustered from Variation 1).
Required tools
Any standard generative AI text model.
Frequently asked questions
What exactly is a Zero Day?
A Zero Day is a fully blank square on your calendar. You wake up without an alarm, you don't have anywhere to be, and you decide what to do in the moment. It is the buffer that absorbs travel fatigue. What if an activity requires a strict reservation? That activity automatically becomes your Anchor for the day. The anchor-and-flex method is built entirely around accommodating those hard, unmovable deadlines while keeping the rest of the day fluid. Can I have more than one Anchor? You can, but it increases the fragility of your plan. If you have a morning anchor and an afternoon anchor, a delay in the morning forces you to sprint to the afternoon one, recreating the stress you were trying to avoid.
Recommended follow-up prompts
"Take my list of Flex activities and sort them by 'High Energy' vs 'Low Energy'." "Identify any of my Anchor activities that are highly weather-dependent."
Tags and categories
Tags:
pacing, scheduling, anchor and flex, burnout prevention, travel planning Categories: Time Management, Travel & Lifestyle
Citations
NOT APPLICABLE
The Deadlined Itinerary Generator
Generate a complete day-by-day itinerary with a reservation booking calendar.
Even the most beautifully paced, geographically perfect itinerary shatters if you show up to a Michelin-starred restaurant without a reservation, or try to walk into a famous museum that sold out of timed-entry tickets three months ago. The hardest part of advanced planning is knowing when to book things. This advanced prompt acts as a strategic architect. It takes your dates, your lodging, and your wishlist, and produces a structured day-by-day plan with explicit pacing rules, while pulling out a critical "Book By" calendar based on typical reservation patterns.
Why this matters now
Travelers frequently miss out on marquee experiences because they didn't realize booking windows open 60 or 90 days in advance. By running this prompt months before you leave, you generate a strategic timeline. You get the structure of the trip, plus an actionable calendar of deadlines, ensuring you never lose out on a core memory just because you didn't know the rules of the game.
Act as an expert travel strategist. I am traveling to \[Destination\] from \[Start Date\] to \[End Date\], staying in \[Lodging Neighborhood\]. I want to build a resilient, map-aware itinerary from this wishlist: \[Insert List\].
Construct a day-by-day structured plan applying the following rules:
> 1. Cluster stops geographically so I start near my lodging and move logically.
> 2. Pace each day with exactly ONE 'Anchor' (must-do) and ranked 'Optional Flexes'.
> 3. Provide a 'Backup Option' for each day in case of bad weather or sudden closures.
CRITICAL CONSTRAINT: Do not state current venue opening hours, claim specific availability, or assert live transit times.
Instead, provide two things after the itinerary:
A. A 'Logistics to Verify' list: specific transit estimates I need to check on a map app, and hours/closure days I must look up on official sites.
B. A 'Reservation Lead-Time Calendar': Analyze the types of venues on my list and tell me the *pattern* for how far in advance they typically book out (e.g., 'Marquee fine dining: typically 60 days ahead'). Sort my wishlist into a booking deadline calendar based on these industry-standard patterns, so I know what to research and book today versus what I can walk into.
How the AI reads this prompt
Practical examples from different industries
Honeymoon Planners:
A couple going to the Amalfi Coast needs to balance relaxation with high-demand activities. The AI sequences a boat tour and a cliffside dinner on separate days to avoid rushing. The Lead-Time Calendar alerts them that the specific Michelin-starred restaurant they want typically opens reservations 90 days in advance, and the private boat charters usually book out a month ahead, prompting them to lock those down immediately. Multi-Generational Families: A family of twelve traveling to London uses this to manage chaos. The AI clusters a Tower of London Anchor with nearby pub Flexes. The Backup Option provides an indoor museum if it rains. The Lead-Time Calendar warns the designated planner that finding a dinner reservation for twelve people requires booking at least six weeks in advance, preventing a crisis of being turned away from restaurants at 7:00 PM. Music Festival Goers: Travelers attending a destination festival use the prompt to plan the days around the event. The AI makes the festival grounds the Anchor, and provides nearby late-night food as Flexes. The Lead-Time Calendar reminds them that hotels and rental cars in festival cities often book out six months in advance, prompting immediate action.
Creative use case ideas
- National Park Road Trips: Mapping out campsite check-ins and hiking trails, where the Lead-Time Calendar is vital because federal campsites often book up exactly six months to the day in advance.
- Ski Vacations: Structuring days around mountain passes and equipment rentals, checking patterns for when early-bird lift tickets go on sale.
- Broadway/Theater Trips: Pacing show times with pre-theater dinners, using the calendar to know when to enter ticket lotteries versus buying premium seats.
Adaptability tips
If you are planning a highly spontaneous trip, you can tell the AI to "Optimize for walk-ins" in the prompt. It will adjust the itinerary to focus on parks, public spaces, and casual dining, minimizing the amount of advance booking required.
Pro tips
Ask the AI to cross-reference your Lead-Time Calendar with your Zero Day. If a high-demand activity can only be booked on your scheduled Zero Day, you can manually swap the days around before your trip begins.
Prerequisites
You need a confirmed destination, dates, lodging location, and a budget ceiling. You also need a comprehensive wishlist of desired activities.
Required tools
A capable AI model like Claude 3.5 Sonnet, ChatGPT-4o, or Gemini 1.5 Pro.
Frequently asked questions
Why does the AI know booking patterns but not live availability?
AI models are trained on vast amounts of internet text, which includes millions of articles saying "You have to book this restaurant 60 days out." It learns the rules of booking. But it does not have a live connection to the restaurant's actual booking database to see if a table is free right now. What should I do if the 'Backup Option' is also outside my geographic cluster? If the AI provides a backup that is too far away, simply reply: "The backup option for Day 3 is too far. Please provide a backup option that is within a 15-minute walk of the Anchor activity." Can I trust the Lead-Time Calendar completely? No, use it as an early warning system. If the AI says a museum books out 30 days in advance, go to the museum's website today and confirm their exact policy. The AI provides the pattern; you verify the reality.
Recommended follow-up prompts
"Take the Lead-Time Calendar and format it as a markdown table with columns for 'Item', 'Typical Booking Window', and a blank column for 'Confirmed Date'." "Review the Backup Options provided and flag any that would break my budget ceiling."
Tags and categories
Tags:
advanced itinerary, reservation deadlines, day-by-day plan, travel strategy, risk management Categories: Project Management, Travel & Lifestyle
Citations
NOT APPLICABLE
Which of the three should you use?
The Beginner prompt is a spatial tool. It is designed to take the chaos of a wishlist and impose geographic order, ensuring you don't spend your vacation stuck on a subway. It is perfect for early-stage planning when you just need to see what is possible. The Intermediate prompt is a psychological tool. It focuses on pacing and energy management, utilizing the anchor-and-flex method to build a schedule that can survive a late start or a long lunch. It is best for travelers who have their list grouped but know they have a habit of burning themselves out. The Advanced prompt is a comprehensive logistical system. It combines the geographic clustering of the beginner tier and the pacing rules of the intermediate tier, and adds a critical layer of forward-looking strategy: the reservation deadline calendar. This is the prompt for the designated trip planner who needs to know what to book today, what to verify tomorrow, and what to leave to chance.
Gemini's post shipped with escaped markdown in its reader prompts. The post as delivered contains 30 backslash-escaped characters, 20 of them inside the three prompts you are meant to copy — so the placeholders read \[Destination\], \[Neighborhood/Area\], \[Insert List\], \[Number\], \[Start Date\], \[End Date\] and \[Lodging Neighborhood\] instead of [Destination], [Neighborhood/Area] and the rest.
Paste one of those prompts into a chatbot and the backslashes go with it. They are harmless — every model will read straight through them — but they are not what Gemini meant to write. The remaining ten escapes sit in the commentary around the prompts, where they show up as things like 1\. in a numbered list and \pattern\ where italics were intended.
The judge did not mention this and it had no part in the scoring. This week's judge was Gemini itself, and it placed its own post third — on depth of content, not on formatting.
We have not corrected the post. Ketelsen.ai is an experiment in what these models actually produce from an identical brief, so what they produce is the finding — including the untidy parts. Editing it, or telling the models in advance not to do it, would quietly delete the observation.
Worth noting, five weeks in: Gemini has emitted escaped markdown in every week of this series except the first, and Claude has emitted none in any week. That is a real and persistent difference between the two, and it is the kind of thing this series exists to surface.
TAGS:
