Pick the cheapest store and best credit card for each purchase with a ChatGPT project

WorkedEvidence: Described by posterPosted Oct 9, 2026Last checked Nov 7, 2026

Shubham Sharma's ChatGPT project compares retailer prices and bank offers on each card to choose where to buy and how to pay.

Source checked Nov 7, 2026
Results shared

How to use this

Tap Copy prompt.
Open ChatGPT.
Paste it into the message box.
Replace anything in [CAPITAL LETTERS IN BRACKETS] with your own details.
Send it, then read the answer before acting on it.

New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

Here are my cards by series with their rewards, fees and benefits (no card numbers): [LIST]. I want to buy this product: [LINK]. Check other retailers for a better price, check current bank offers for my specific cards, and compare instant discounts, cashback and points to tell me where to buy and which card to use.

Try this in:

ChatGPT Used in source Gemini Grok Claude

This prompt has blanks to fill in, like [LIST]. We'll copy it instead of filling it in, so you can edit it before you send.

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, Anthropic or xAI, and your results may not match the source.

Optional stronger version

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

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Find where to buy something and which of my cards gives the best deal.

Questions to ask me first:
- Which cards do you have, by series or name only?
- What do you want to buy, and by when?
- Do you value cashback, points or instant discounts most?

Inputs (fill in or confirm):
- Cards: [ISSUER, SERIES, REWARDS, FEES; NO NUMBERS]
- Product: [LINK OR MODEL]
- Delivery deadline: [DATE]
- Preference: [CASHBACK, POINTS OR DISCOUNT]

Rules:
- Never ask for or store full card numbers.
- Link every price and bank offer you cite.
- Check offer conditions such as minimum spend and eligible cards.
- Compare the final cost after discounts, not the headline price.

Checkpoint: Show the price comparison before the card recommendation.

If you get stuck: If an offer's terms are unclear, say so and don't count it.

Verify before you finish: The recommended store and card give the lowest final cost you can source.

Output: A table of store, price, eligible offer and final cost by card, plus one recommendation.

Done when: I know exactly where to buy and which card to use.

AI tool

ChatGPT

Outcome

Shubham Sharma, a self-described nerd for deals, built a personal credit card optimizer as a ChatGPT project. It keeps a list of Sharma's credit and debit cards by card series, not card number, with their rewards, fees and benefits. When Sharma wants to buy something, Sharma adds the product link; ChatGPT scans retailers for better prices, checks current bank offers against those specific cards, and compares instant discounts, cashback and reward points to say where to buy and which card to use. It now runs as an ongoing skill in the project, so Sharma no longer checks a dozen bank offers by hand or finds out at checkout that a card isn't eligible.

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

Source

Posted: Oct 9, 2026 by Shubham Sharma (The Rundown community)
Last checked: Nov 7, 2026
Method:: How we verify

https://app.therundown.ai/community/posts/4fca3ac0-98cc-4d3d-b54c-406c035fa834

Context: Posted to The Rundown community (date from the post's UTC timestamp). The author is in India; the post doesn't give example savings.