Boot Camp Week 7: Apps You Use

Use AI to build a spreadsheet you can actually download, then check that different cost categories are using the right logic before you trust the totals.

Week 7 of the AI, Eh? Summer Boot Camp is Apps You Use, Word, Excel, and Google. AI does not have to live in its own separate tab, it can help you build things you actually use every day, like the spreadsheet nobody wants to build by hand.

Quick reminder of the shape, same every week. A detailed prompt you copy and paste. An iteration showing you how to fix it. Something personal you apply it to. And a Prompt Card you save to your toolkit.

Grab your toolkit document. We are adding Card 7. Let’s go.

Six things every good prompt needs

Same checklist as every week. Watch for all six in the prompt below.

1. Give it context. Who is involved and what is actually going on, anything AI could not otherwise know.

2. Be specific about the task. Not “help me with a spreadsheet,” exactly what you want it to produce.

3. Set your real constraints. The real numbers involved, whatever actually shapes the situation.

4. Tell it the format you want back. A formula, a table, plain steps. Do not let it guess.

5. Ask it to flag uncertainty. Anything it is not fully sure about, so you know what to double check yourself.

6. Protect your privacy. Skip anything that could identify you personally, like your full name or address.

Step 1: Run this prompt exactly as written

Open ChatGPT or Claude, both can build you an actual downloadable spreadsheet now, not just a formula. Paste the whole thing below in exactly as written, and hit enter.

“My family and two other families are splitting costs for a shared cottage trip this summer. Build me a downloadable Excel spreadsheet that tracks everything. Here’s what we need to split: the cottage rental is $2,400 total, and my family is staying 6 nights, Family B is staying 4 nights, and Family C is staying 3 nights, so that cost should be split based on nights stayed. We’re also splitting $450 in shared groceries and $180 in gas for a group supply run, both of which should be split evenly across all three families since everyone shares those regardless of how many nights they’re there. There’s also a $300 cleaning and damage deposit that should also be split evenly. Build the spreadsheet so each cost category is broken out clearly, show how much each family owes for each category, and give me a final total per family at the bottom. Use Family A, Family B, and Family C instead of real names. Flag anything you’re not sure about, especially how you handled the different splitting logic for each category.”

Step 2: Here is how you fix it when it is not quite right

You will probably get back a clean looking spreadsheet with all four categories broken out. Look closely at the logic behind each one though. AI has a habit of grabbing onto the first splitting rule it sees, nights stayed, and applying it everywhere, even to groceries and gas, which should be split evenly since everyone shares those regardless of how long they are actually there.

This is exactly the moment to speak up, in one line, in the same conversation.

“Groceries and gas need to be split evenly across all three families, not by nights stayed. Only the cottage rental should use the nights based split. Can you fix the spreadsheet so each category uses the right logic.”

One sentence, pointed at the exact gap. The corrected totals should land somewhere close to $1,418 for your family, $1,048 for Family B, and $864 for Family C, once the cottage rental is split by nights and everything else is split evenly. Always check that a spreadsheet like this is actually applying different logic to different categories, not just repeating whatever rule it used first.

Step 3: Build your own, then save it as a Prompt Card

Now think of something real you could actually have AI build for you as a spreadsheet, splitting a set of costs, tracking a list, running numbers you have always done by hand. In your head, walk through it. What is actually going on. What you actually want back. Your real numbers, whatever shapes the situation, including anything that needs to be split using different rules. How you want it formatted. What you want it to double check before you trust it. And keep it anonymous, generic labels instead of real names.

Now say all of that out loud as one real paragraph, the way you would actually explain it to a friend. That is your prompt. Paste it in and run it, and download the spreadsheet it builds you.

Once you have a result, ask yourself two quick things. Did anything come back not quite right? If so, what one line did you send to fix it?

Now open your toolkit document, add a heading called Prompt Card 7, and write out these four things yourself, based on what you just did.

What this is for. One line, plain language, describing your real situation.

The prompt. The real paragraph you wrote and ran.

The fix that got it there. The one line you sent to correct it, if you needed one.

When to use it again. One line reminding future you when this applies.

That is Prompt Card 7, done. Seven real, working prompts in your toolkit now, each one proven on your own life.

Coming up next week

Week 8 is What’s Next, the final week. We are going to look back at everything you built and talk about where to go from here. Bring your toolkit document, Prompt Card 8 is last.

AI assisted. Human led.

Whatever AI produces for you, always read it, verify it, and make it sound like you. AI is an incredible first draft machine. Your judgment, your voice, and your values are always the final layer.

Hit reply and tell me what your Prompt Card 7 turned out to be. I read every single one.