# classify | In-browser AI by Shubham Prakash

> Write a playbook of categories and rules, drop in a spreadsheet, and get every row decided. Unsure rows queue for review, and files never leave the tab.

Page: https://shubhamcodess.github.io/builds/classify/

## classify

Write a playbook of categories and rules, drop in a spreadsheet, and get every row decided. Unsure rows queue for review, and files never leave the tab.

- Page: https://shubhamcodess.github.io/builds/classify/
- Kind: In-browser AI, 2026
- Stack: JavaScript, transformers.js, WebGPU
- live: https://shubhamcodess.github.io/classify/
- code: https://github.com/shubhamcodess/classify

### Overview

Write a **playbook** of categories, decisions and rules, then drop in Excel, CSV, JSON or logs. It fills in each row, **queues the unsure ones** for you, and hands back **the same file with new columns**. Everything runs in the tab.

### What it does

- Rules always win. Then a word-based model, then embedding similarity, then an optional second opinion from a larger model on unsure rows.
- A review queue with a reason for every row, and your corrections become training examples.
- Excel comes back as the same workbook, with other sheets, formatting and formulas kept.

### How it is built

- Measured on held-out lines: categories 93% of 29, ticket decisions 87% of 45.
- Mixing weights were tuned on separate lines before the test set was run.
- Models live in the browser's private file system and projects in IndexedDB.

### Honest limits

- The test sets are tiny and hand-labelled.
- The larger model is 847 MB and needs WebGPU.

By Shubham Prakash: https://shubhamcodess.github.io/
