Real Agent Cases

Build a university decision matrix for a daughter choosing between four schools, using Grok for data

Posted
by Mark Zolna (LinkedIn)
Last checked
Method:
How we verify

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Outcome

A parent built a one-page decision matrix to help his daughter choose between the four universities that accepted her, using Grok as the data source and factoring in Florida's Bright Futures scholarships. He shared it so she could adjust the scoring and add criteria herself.

Agent

Grok

Prompt Recreated prompt

The source didn't share its exact prompt, so we wrote this from what it describes.

Let's work this out together. I'll tell you what I know, you suggest options and ask what you need, and we'll narrow it down step by step. Nothing gets booked, bought or sent until I say so.

Goal: Let's build a one-page decision matrix to compare the schools my child got into.

What I'll share as we go:
- The schools
- What matters to my child (cost, programs, location, size, etc.)
- Scholarships or aid offered

Rules:
- Gather data for each school from official sources and cite them.
- Use clear weights my child can change.
- Show net cost after scholarships separately from rankings.
- Keep it to one page.
- If a site asks for a login, a CAPTCHA or payment details, stop and hand control back to me.
- Ask for my OK before you pay, book, send, submit or cancel anything.
- Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify.

Output: A weighted comparison table with sources and an editable scoring column.

You'll know it worked when: my child can change the weights and see which school comes out ahead.

Try this in:

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Let's work this out together. I'll tell you what I know, you suggest options and ask what you need, and we'll narrow it down step by step. Nothing gets booked, bought or sent until I say so.

Goal: Let's build a one-page decision matrix to compare the schools my child got into.

What I'll share as we go:
- The schools
- What matters to my child (cost, programs, location, size, etc.)
- Scholarships or aid offered

Rules:
- Gather data for each school from official sources and cite them.
- Use clear weights my child can change.
- Show net cost after scholarships separately from rankings.
- Keep it to one page.
- If a site asks for a login, a CAPTCHA or payment details, stop and hand control back to me.
- Ask for my OK before you pay, book, send, submit or cancel anything.
- Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify.
- Confirm aid and scholarship amounts with each school's financial aid office.

Output: A weighted comparison table with sources and an editable scoring column.

You'll know it worked when: my child can change the weights and see which school comes out ahead.

Before you finish: re-read my goal and constraints, check your answer against each one, and list anything you assumed or couldn't confirm.

Source

https://www.linkedin.com/posts/markzolna_my-daughters-university-choice-decision-activity-7303423775834845184-3x7x

  • A Hacker News commenter had four home-repair bids with wildly different line items, costs, timelines, scopes and formats. Claude (Opus) turned them into an apples-to-apples comparison, filled gaps with reasonable inferences from the other bids, produced a PDF they printed to go through with their partner, and suggested key questions for follow-up calls. The commenter says it clearly showed the advantages of one of the bids.

    Claude · Personal · Source date:

  • Chris L.'s family spent about $19k on healthcare in a year that wasn't especially bad health-wise, because they'd hit the out-of-pocket maximum on a plan that didn't fit their needs. During open enrollment they photographed the pricing and coverage pages of the enrollment booklet and gave them to ChatGPT, with the care they expected. After 5 and a half minutes it compared the PPO, Gold and Bronze plans, explained how an FSA and an HSA would work out, and gave best- and worst-case yearly costs for each. They then asked about the costs in between those two extremes and got another detailed answer. They checked the output with two other models, which gave the same numbers, and expect to pay between $2,600 and $16,500 in 2026, saving at least $2,500 compared with the year before. It took them under 20 minutes.

    ChatGPT · Personal · Source date:

  • Helping their parents review Medicare coverage for 2027, Matthew Guldin gathered details on coverage, prescriptions and doctors and used ChatGPT to organize it, build a checklist, explain enrollment requirements and flag areas to research. It pulled together information spread across many sites and raised questions Guldin hadn't considered, but comparing its answers with official Medicare enrollment information showed several mistakes and omissions, including leaving out one of their father's important medications when evaluating Part D drug coverage.

    ChatGPT · Personal · Source date: