Landing the Plane: Budget Post-Mortems and the Reusable System
WEEK 99 :: 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: "Landing the Plane" — Post-Trip Reconciliation and the Reusable System.
This is Week 8, the final week of an eight-week series on planning a vacation with AI. The trip is over. This week is about closing it out well and, more importantly, about keeping what the reader just built — turning eight weeks of one-off prompts into a personal, reusable system so the next trip takes a fraction of the effort. This is the payoff the whole series was pointing at.
There are two jobs. The first is reconciliation: a budget post-mortem comparing what was planned against what was actually spent and finding where the estimates were wrong; and the recovery work of disputing incorrect charges and pursuing any compensation the reader is owed — a delayed flight, a resort fee that was never disclosed, a charge that does not match what was agreed. The second job is the durable one: taking the workflow the reader has now lived through and compressing it into a template they can run again, so the knowledge does not evaporate the moment they unpack.
The deliverable the reader should walk away holding is twofold: a clear post-trip reconciliation — what was spent versus planned, what to dispute and how — and a reusable personal trip-planning template distilled from the eight-week process, ready to run for the next destination.
The three prompts should help a reader:
- Run the budget post-mortem. Compare planned against actual from the reader's own records, surface where the plan was optimistic, and turn that into a sharper set of assumptions for next time — the AI structuring the comparison from numbers the reader supplies, not inventing what a trip "should" cost.
- Pursue disputes and claims, methodically. Organise a charge dispute or a delay claim into who to contact, what evidence to attach, and what to ask for, in a calm and orderly sequence — while pointing the reader to the airline, card issuer, or platform to confirm what they are actually entitled to rather than asserting it.
- Build the reusable template. Distil the eight-week workflow into a personal, repeatable planning system — the steps, the prompts worth keeping, and the reader's own hard-won preferences — so the next trip starts from a framework instead of a blank page. This is the series' real lesson: a good prompt, saved and adapted, becomes a system.
At the advanced tier, the strongest version of this week is a written, reusable planning template the reader can save and re-run — the whole series compressed into a sequence of steps and prompts tuned to how this traveller actually plans, plus a reconciliation summary that feeds next time's estimates. That structure is worth reaching for, and it is the natural landing point for a series about turning one-off AI help into a repeatable method.
A hard constraint, carried through to the last week. AI models cannot see the reader's actual receipts, a specific carrier's current compensation policy, or the rules that govern a particular claim, and these are jurisdiction- and date-specific. No prompt may ask the AI to confirm a specific compensation entitlement, promise a payout, adjudicate whether a charge is disputable, or state current claim rules as settled fact. The dispute and claim prompts should give the reader an organised process and the right questions — and send them to the airline, card issuer, or regulator to confirm — not a verdict on their case.
Design the prompts so the AI does what it is genuinely good at: structuring a reconciliation from supplied numbers, organising a dispute into an orderly sequence, and compressing a lived process into a reusable template. The reader supplies their records and their experience; the AI supplies structure, sequence, and the distilled system. Posts whose prompts have the AI assert entitlements or invent costs should expect to be marked down on Practical Utility and Content Accuracy.
Series dependency chain, for the Metadata block: Week 8 consumes the entire trip — the budget ceiling from Week 1 (to reconcile against), the bookings and protection work from Weeks 3, 4 and 6 (for disputes and claims), and the in-trip record from Week 7 (what actually happened and what it cost). Week 8 produces the reusable planning template — the series' closing artifact — which has no successor week because it is the thing designed to start the next trip's Week 1.
Because readers may arrive at this post having only just returned, without having read the earlier weeks, the prompts should work for someone who simply has their receipts and a sense of how the trip went, while making clear the reusable template is far richer when it is distilled from the full process.
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. A family reconciling a trip's spending against the plan, a traveller pursuing a delayed- flight claim, a couple disputing an undisclosed resort fee, and anyone building a personal template so the next trip is easier 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 claims-and-entitlements constraint above, this is a bad week to invent any — if you find yourself reaching for a compensation amount or a typical trip cost, that is the signal to restructure the prompt so the reader supplies the real number and confirms entitlements at the source.)
## 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: 8` 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 confirm a compensation entitlement, promise a payout, adjudicate whether a charge is disputable, or state current claim rules as settled fact. Those must be a process and questions the reader confirms with the airline, card issuer, or regulator.
We have reached the end of the journey. The bags are unpacked, the trip is over, and now it is time for the most important step: landing the plane. This week is all about reconciliation and recovery—from running a budget post-mortem to methodically organizing dispute claims without the headache. More importantly, we are turning eight weeks of one-off prompts into a personal, reusable system so your next vacation takes a fraction of the effort. Whether you need a simple spending breakdown, a structured way to pursue a delayed flight, or an advanced, durable planning template, these three prompts ensure your hard-won travel knowledge never evaporates.
The Budget Post-Mortem
Compare your planned vacation budget against your actual spending effortlessly.
Nobody likes looking at their bank statement after a long trip. It is easy to just pay the credit card bill and ignore where the budget leaked. But the only way to plan better for the next trip is to honestly assess where the last one went off the rails. This prompt takes the sting out of the math, giving you a clear, judgment-free breakdown of your spending.
Why this matters now
Right now, you are sitting on a pile of receipts and a vague memory of what you meant to spend. Running this prompt today gives you immediate clarity on your travel habits and creates a sharper set of assumptions for your next adventure.
I have just returned from a vacation and need to run a budget post-mortem. I will provide my original budget estimates followed by my actual spending in various categories. Do not invent any costs or judge the spending. Simply structure a clear comparison showing the variance (over or under budget) for each category, and provide a brief summary of where my estimates were the most optimistic.
How the AI reads this prompt
"I have just returned from a vacation and need to run a budget post-mortem."
This sets the immediate context and goal for the AI. Without it, the model does not know the phase of the trip and might try to offer forward-looking booking advice instead of focusing on reconciliation.
"I will provide my original budget estimates followed by my actual spending in various categories."
This establishes the data source. Without this, the AI might hallucinate average trip costs instead of waiting for your exact numbers.
"Do not invent any costs or judge the spending."
This enforces a strict constraint on the AI's behavior. Without this boundary, the AI can sometimes inject moralizing language about overspending or make up missing figures, which ruins the utility of the prompt.
"Simply structure a clear comparison showing the variance... and provide a brief summary of where my estimates were the most optimistic."
This defines the exact output format. If omitted, you might get a messy paragraph instead of a clean, scannable breakdown of your financial blind spots.
Practical examples from different industries
A family returning from a theme park vacation can use this prompt by pasting their initial budget and their actual credit card statement. The AI will output a clean chart showing exactly how much the daily character breakfasts blew past the original dining estimates, giving them a realistic food baseline for next year. A solo backpacker who toured Europe can input their hostel and train budget versus actuals. The AI will highlight the variance, revealing that while accommodation was under budget, impromptu regional rail tickets caused a massive overrun.
Creative use case ideas
- Evaluating a home renovation project's budget versus actual material costs.
- Reviewing a community fundraiser's operational expenses compared to the initial projections.
- Analyzing a semester's living expenses for a college student adjusting to off-campus life.
Adaptability tips
You can adapt this prompt by asking the AI to output the final comparison as a CSV format, making it easy to paste directly into Excel or Google Sheets for permanent record-keeping.
Pro tips
NOT APPLICABLE
Prerequisites
You must have your original budget ceiling from Week 1 and your actual trip records from Week 7 ready to paste into the chat.
Required tools
Any standard AI text model (ChatGPT, Claude, Gemini).
Frequently asked questions
What if I forgot to track some of my cash spending? You can simply add a "Miscellaneous Cash" category to your actuals with your best estimate. The AI will work with the numbers you provide, though your final variance will only be as accurate as your input. Will the AI store my financial data? Be mindful of the platform you use. It is best practice to omit highly sensitive information like account numbers, and simply paste category totals rather than raw bank exports. Can I use this for non-travel budgets? Absolutely. The core instruction is just comparing planned versus actual numbers, which works for groceries, events, or monthly household tracking.
Recommended follow-up prompts
"The Spending Habit Analyzer" \- A prompt to identify behavioral triggers that lead to budget overruns based on the discovered variance.
Tags and categories
Tags:
Budgeting, Post-Trip, Reconciliation, Finance. Categories: Travel Planning, Personal Finance.
Citations
NOT APPLICABLE
The Dispute and Claim Organizer
Methodically organize your charge disputes and delay claims without the stress.
Travel hiccups happen, but fighting for compensation should not require a law degree. Whether it is an undisclosed resort fee or a significantly delayed flight, staring down a customer service form can feel overwhelming. This prompt helps you organize your evidence and your asks into a calm, orderly sequence so you can confidently approach the airline or card issuer.
Why this matters now
You have returned home and realized a charge does not match what was agreed upon, or you suffered a severe delay. This prompt organizes your raw experience into a methodical action plan today, saving you hours of frustrated phone calls and drafting.
I need to organize a claim regarding a recent travel issue. I will provide the details of what happened, the service provider involved, and the receipts or emails I have. Please help me structure a methodical timeline of events and draft a clear, factual summary I can use to contact the provider or my credit card issuer. Do not assert specific legal entitlements, promise a payout, or adjudicate the dispute. Simply outline who I should contact first, what evidence I need to attach, and what neutral, fact-based questions I should ask them to confirm my compensation eligibility.
How the AI reads this prompt
"I need to organize a claim regarding a recent travel issue. I will provide the details..."
This sets the AI's role to an organizer of provided facts. Without it, the model might try to search the web for airline news instead of focusing on your specific situation.
"Please help me structure a methodical timeline of events and draft a clear, factual summary..."
This directs the AI to create actionable, structured output. Without this request, the AI might just offer sympathetic platitudes rather than a usable communication draft.
"Do not assert specific legal entitlements, promise a payout, or adjudicate the dispute."
This is a critical guardrail. AI models cannot see a specific carrier's current policy or know your jurisdiction's exact rules. Without this, the AI might confidently guarantee you a refund that does not actually exist, setting you up for failure.
"Simply outline who I should contact first, what evidence I need to attach, and what neutral, fact-based questions I should ask..."
This ensures the output is a practical checklist. Without it, the AI might write an overly aggressive legal demand letter instead of a calm, orderly inquiry.
Practical examples from different industries
A couple returning from a resort discovers a resort fee on their final bill that was never disclosed during booking. They feed their booking confirmation and final receipt details into the prompt, and the AI structures a factual summary for them to present to their credit card issuer for a chargeback inquiry. A traveler whose flight was delayed overnight feeds their original itinerary and the airline's delay notifications into the prompt. The AI organizes a chronological timeline of the delay and drafts a polite message asking the airline to clarify their compensation policy under current regulations, without inventing a payout amount.
Creative use case ideas
- Organizing a timeline of events for an insurance claim after a minor fender-bender.
- Structuring a formal complaint to a contractor who failed to complete a home repair on schedule.
- Drafting an inquiry to a utility company about an unexplained spike in a monthly bill.
Adaptability tips
If you are dealing with a platform rather than a direct provider, you can modify the prompt to ask the AI to specifically tailor the communication for a third-party mediation platform's specific resolution center.
Pro tips
NOT APPLICABLE
Prerequisites
You need the booking and protection details established in Weeks 3, 4, and 6, along with any in-trip records of delays or unexpected charges.
Required tools
Any standard AI text model.
Frequently asked questions
Why shouldn't I just ask the AI what I'm owed? Because AI models hallucinate policies. Claim rules are jurisdiction- and date-specific, and a carrier's compensation policy can change. The AI is great at organizing your argument, but you must confirm the actual rules with the source. Will this guarantee I get my money back? No. This prompt provides you with an organized process and the right questions to ask, not a verdict on your case. It makes you a highly prepared consumer, which improves your odds, but the final decision rests with the issuer or provider. Should I upload photos of my receipts to the AI? It is safer and just as effective to manually type out the relevant details (dates, amounts, merchant names) rather than uploading unredacted photos that might contain your full payment information.
Recommended follow-up prompts
"The Escalation Email Framer" \- A prompt for restructuring your inquiry if the first customer service tier denies your initial request.
Tags and categories
Tags:
Claims, Disputes, Organization, Travel Issues. Categories: Travel Planning, Problem Solving.
Citations
NOT APPLICABLE
The Reusable Personal Planning System
Compress your entire eight-week experience into a personal, repeatable template.
You have just spent eight weeks learning how to prompt your way through budget ceilings, itinerary building, and risk mitigation. If you stop here, you will have to start from a blank page the next time you want to take a vacation. The real power of AI is not in one-off answers; it is in building durable systems. This prompt distills everything you have learned and your hard-won personal preferences into a master framework.
Why this matters now
Your trip is fresh in your mind, and you know exactly what worked and what did not. By running this prompt now, you capture that knowledge before it evaporates, ensuring your next trip takes a fraction of the effort.
I have just completed a multi-week travel planning process using AI, culminating in a finished trip. I want to build a written, reusable planning template that I can save and re-run for my next destination. I will provide a summary of the steps I took, the AI prompts that worked best for me, my personal travel preferences (like pacing and budget style), and the post-mortem reconciliation of what I actually spent versus what I planned. Distill this entire workflow into a sequential, repeatable master system. Format it as a step-by-step guide containing my customized base prompts, leaving bracketed placeholders for future destinations and dates, so I never have to start from a blank page again.
How the AI reads this prompt
"I want to build a written, reusable planning template that I can save and re-run for my next destination."
This tells the AI that the goal is an enduring artifact, not a quick answer. Without this, the model might just summarize your recent trip rather than building a forward-looking tool.
"I will provide a summary of the steps I took, the AI prompts that worked best for me... and the post-mortem reconciliation..."
This establishes the rich context the AI will consume. Without feeding it the full lived process, the AI would generate a generic, unhelpful planning list.
"Distill this entire workflow into a sequential, repeatable master system."
This forces the AI to prioritize structure and order. Without it, you might receive a disorganized brain-dump of travel tips instead of a step-by-step framework.
"Format it as a step-by-step guide containing my customized base prompts, leaving bracketed placeholders..."
This is the secret sauce. By asking for bracketed placeholders, you ensure the output is a true template ready to be copied and pasted next year. Without this, the AI will not templatize the prompts, requiring you to manually rewrite them later.
Practical examples from different industries
A family who just completed a complex multi-city road trip feeds their successful itinerary prompts, their realization that they need mandatory down days, and their budget realities into the prompt. The AI outputs a master Family Road Trip Template containing pre-written prompts adjusted for their newly discovered pacing needs. A frequent solo traveler uses the prompt to lock in their specific preferences for boutique hotels and public transit routing. The AI generates a master document they can deploy every time they pick a new city, cutting their planning time from days to hours.
Creative use case ideas
- Creating a reusable master template for organizing annual corporate retreats.
- Building a repeatable system for planning complex holiday dinners or large family reunions.
- Developing a standardized framework for launching new freelance client projects, complete with tailored onboarding prompts.
Adaptability tips
Store the output of this prompt in a dedicated notes app and update it after every single trip. The system should evolve as your travel style changes over the years.
Pro tips
NOT APPLICABLE
Prerequisites
You need the entire journey's context—your budget from Week 1, the booking and protection work from Weeks 3, 4, and 6, the in-trip record from Week 7, and your budget post-mortem from this week.
Required tools
Advanced AI models (Claude 3.5 Sonnet, GPT-4o, Gemini 1.5 Pro) are best suited for maintaining this level of structural consistency.
Frequently asked questions
Do I have to type out every single prompt I used over the last eight weeks? No. Just copy and paste the few prompts that were the most useful to you, and summarize the rest. The AI will weave them into the master structure. What if my next trip is a completely different style? The master system handles the workflow framework (budgeting, booking, protection, packing). You will simply change the variables inside the bracketed placeholders when you run it next time. Can the AI store this template for me? Most AI chats eventually fall out of context or get deleted. You must copy the final output and save it in your own permanent digital files to truly own the system.
Recommended follow-up prompts
"The Variable Injector" \- A prompt to quickly feed new destination data into your master template placeholders.
Tags and categories
Tags:
Systems, Automation, Templates, Master Framework. Categories: Prompt Engineering, Travel Planning.
Citations
NOT APPLICABLE
Which of the three should you use?
These three variations represent the final phases of a well-executed trip, taking you from immediate review to long-term leverage. The Beginner variation focuses purely on looking backward, helping you do the math on your budget without judgment so you can identify your financial blind spots. It is a straightforward tool for immediate clarity. The Intermediate variation steps into problem-solving mode, providing a calm, orderly framework for tackling disputes or claims. It bridges the gap between frustration and action by organizing your evidence into a factual timeline, ensuring you approach customer service confidently without overstepping into hallucinated policies. The Advanced variation is the true capstone of the series. Instead of just answering a question, it builds a durable asset. By distilling everything you learned into a repeatable template, it ensures the time you invested over the last eight weeks continues to pay dividends on every future trip you take.
TAGS:
