Skip to content
TriedPrompts

More in Spreadsheets & money data.

Rebuild a Mint-style expense tracker with ChatGPT, Sheets and Looker

WorkedEvidence: Described by posterPosted Last checked

Edgar Ramirez Vilchez used ChatGPT to script Fidelity CSV cleanup, then Looker Studio charts, as a personal Mint replacement.

How to use this

  1. Tap Copy prompt.
  2. Open ChatGPT.
  3. Paste it into the message box.
  4. 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.

I have a CSV export of all my expenses from Fidelity. Write a script that categorizes, cleans and enhances the rows the way I specify, and explain how to load the result into Looker Studio for Mint-style charts.

Try this in:

ChatGPT Used in sourceGemini Grok Claude

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open 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, 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: Turn a brokerage/bank expense CSV into categorized data and Mint-style charts without a brittle consumer app.

Questions to ask me first:
- Which categories and merchants need custom rules?
- What charts did you rely on in Mint (trends, net worth, budgets)?
- Prefer Python, Apps Script or Sheets formulas for the cleanup?

Inputs (fill in or confirm):
- CSV export: [FILE]
- Category rules: [LIST]
- Chart list: [TRENDS / BREAKDOWN / OTHER]

Rules:
- Make categorization rules explicit and editable.
- Don't send the full CSV to a model if I ask for local-only processing—generate a script instead.
- Document how to refresh monthly.
- Call out anything Looker can't do that Mint did.

Checkpoint: Show the category mapping on 20 sample rows before processing the full file.

If you get stuck: If a merchant is ambiguous, add an Uncategorized bucket and ask me rather than forcing a label.

Verify before you finish: Monthly totals match the CSV sum after categorization.

Output: A cleanup script, category dictionary and Looker chart setup steps.

Done when: I can refresh the tracker each month from a new CSV.

AI tool

ChatGPT

Outcome

Edgar Ramirez Vilchez missed Mint after its acquisition made tracking worse and other apps needed too much manual category work. Vilchez exported a combined expenses CSV from Fidelity, used ChatGPT to generate a script that categorizes, cleans and enhances the data, then learned Looker Studio to build the charts. After trying Google tools and Lovable, this CSV-plus-ChatGPT-plus-Looker path was the compromise that worked for a personal tracker.

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

Source

Posted
by Edgar Ramirez Vilchez
Last checked
Method:
How we verify

https://craftedforscale.substack.com/p/i-built-a-mintcom-replacement

Context: Recreated from the described pipeline. Self-reported personal finance workflow.

More in Spreadsheets & money data

Similar cases