Software · iOS experiment

Idiot Purchase

A small iOS experiment that turns a receipt into a deliberately theatrical roast of the purchase.

Compendium article 028 Revision 0.6 · July 2026

Budget apps usually respond to a receipt with categories, totals, and charts. Idiot Purchase imagines a less responsible but potentially more memorable response: read the purchase and roast the person who made it.

The project takes the form of a receipt-scanning app concept that reads purchases and generates a humorous critique rather than another budget dashboard. Its purpose is to explore whether mundane personal data can become a lightweight comedic interaction.

The question behind Idiot Purchase

The project is a study in interaction voice. OCR and structured parsing make the joke possible, but the actual product is the timing and specificity of the generated critique—enough to feel personal without becoming cruel or exposing sensitive data. People who enjoy self-directed purchase humor are the intended audience. Receipt subjects and merchants are affected by data handling.

How Idiot Purchase took shape

The small iOS-oriented experiment combines receipt capture or entry, purchase extraction, and AI-generated comedy. Its public demonstration must use synthetic receipts because real examples can reveal payment identifiers, addresses, routines, and private purchasing history. Josiah originated the interaction, tone, and product constraint and directed agent-assisted implementation.

What the evidence supports

A small prototype or project artifact exists, but its current source and reliability require review. The concept illustrates a recurring lesson in tiny apps: personality can be the feature. It also shows why novelty products still need strong privacy defaults and tone controls; a funny output does not justify retaining the document that produced it.

Receipts can expose payment, location, and purchasing details. Public demonstrations must use synthetic data, and generated insults need tone controls. A review of the surviving artifact will show whether the joke still works well enough to merit a demonstration built from fictional purchase data.