---
title: "A Singaporean with no coding skills used Codex to build a tool that picks the best credit card for miles at 3,300 merchants"
person: "Hosan Swee (KiasuMiles)"
tools:
  - "Codex"
  - "ChatGPT"
country: "Singapore"
category: "Save money"
category_slug: save-money
proof:
  - label: "Read Hosan Swee's story in The Straits Times"
    url: "https://www.straitstimes.com/tech/low-on-code-high-on-miles-sporean-uses-ai-to-create-tool-to-maximise-credit-card-rewards"
date: 2026-10-31
date_posted: 2026-09-26
as_claimed: "The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome."
url: "https://agentstories.org/stories/hosan-swee-kiasumiles-codex-credit-card-miles.html"
markdown_url: "https://agentstories.org/stories/hosan-swee-kiasumiles-codex-credit-card-miles.md"
site: "Agent Stories by Solopreneur Code"
---

# A Singaporean with no coding skills used Codex to build a tool that picks the best credit card for miles at 3,300 merchants

Hosan Swee (KiasuMiles) · Singapore · Codex, ChatGPT

## What the agent did

Hosan Swee and his wife share about a dozen credit cards and kept losing miles by picking the wrong one. He used Codex and ChatGPT to build KiasuMiles. Codex scanned bank and merchant websites to build a structured database of card rules, including minimum spend, miles per dollar, eligible categories and monthly caps. People connect KiasuMiles to ChatGPT, Claude or Codex and ask which card to use at a given shop. He built it feature by feature with specific prompts and tested the logic on a few cards first.

## Result, as claimed

The Straits Times reports the tool tracks around 50 credit cards and over 3,300 merchants in Singapore. Compiling the card rules was done in minutes with Codex, compared with the hours it would take by hand. No miles or dollar savings figure is given.

> The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome.

## Proof

- [Read Hosan Swee's story in The Straits Times](https://www.straitstimes.com/tech/low-on-code-high-on-miles-sporean-uses-ai-to-create-tool-to-maximise-credit-card-rewards)

## Try it yourself

Have an AI build a simple table of your own cards' reward rules, then ask it which card to use before you pay.

Prompt:

```text
Here are the credit cards in my wallet: [list]. Using only each bank's official card pages, build a table with card, bonus categories, miles or cashback per dollar, minimum monthly spend, monthly cap and key exclusions. Add the source link and the date checked for every row. Then answer: which card should I use for [merchant and payment method] this month, given I have spent [amounts] on each card so far?
```

Tools:

- [ChatGPT](https://chatgpt.com): Named in the story as one of the tools he used. Fine for a personal version with your own cards
- [Codex](https://chatgpt.com/codex): Named in the story. He used it to scan bank and merchant sites and build the database

Steps:

1. List your cards and ask for the rules table, with a source link on every row.
2. Open each bank page and check the minimum spend and cap yourself.
3. Save the table and ask your card question before big or regular purchases.
4. Refresh the table each month, since banks change rules often.

Watch out: Card rules change and merchant categories are often guessed. Check the bank's terms before a large purchase and do not chase minimum spends you would not otherwise make.

## More

- [This story as a web page](https://agentstories.org/stories/hosan-swee-kiasumiles-codex-credit-card-miles.html)
- [More stories: Save money](https://agentstories.org/categories/save-money.html)
- [More stories from Singapore](https://agentstories.org/countries/singapore.html)
- [More stories that use Codex](https://agentstories.org/tools/codex.html)
- [More stories that use ChatGPT](https://agentstories.org/tools/chatgpt.html)
- [Every story, indexed for AI assistants](https://agentstories.org/llms.txt)
