Skip to content

work / keep-receipt · Live

Keep Receipt

Snap a receipt, AI reads it, your spending explains itself.

Week of Claude Maxing

Play with it

A pure-frontend replica with mock data: nothing is saved, nothing leaves the page. The real app is richer; this is the feel of it.

loading the demo…

The problem

Shoebox receipts and no idea where the money goes, especially across personal and business.

What it does

Photograph a receipt and on-device OCR reads it, with an AI vision fallback only on low confidence. Auto-categorised spend, personal-versus-business tagging, insights, and an Australian tax lens with entity tracking.

The thinking

Target user

Australians juggling personal and business spend (employees, sole traders), starting with me.

Pain points

  • Shoebox receipts and lost deductions at tax time
  • Manual categorising never happens
  • Cloud finance apps want your data on their servers

Gap in the market

A privacy-first, ATO-aware receipt keeper: on-device OCR by default, AI vision only when needed, multi-entity tax lens built for Australian FY rules.

AI + tooling

  • Tesseract.js OCR
  • Kimi vision (fallback)
  • Claude Code (build)
  • Dexie
  • Google Drive backup

Frameworks

  • Capture at the point of action: snap now, categorise never
  • Loss aversion: surfacing the deductions you are about to miss
  • ATO myDeductions parity model with multi-entity tagging
  • Privacy by design: hybrid cheap-local OCR, AI only on low confidence

Success metrics

  • Live and in use
  • TBD: receipts captured, deduction totals surfaced
what I learned
Cheap local first, expensive AI only on low confidence.
next projectMandarin Tutor