Document Intake & Search
Scan physical documents with your phone and search them instantly
Photo to searchable archive in under 5 minutes
The Problem
Paper documents — receipts, business cards, contracts — pile up with no way to search them later. Manual filing is slow and inconsistent.
The Approach
Built a CLI pipeline that watches for phone scans via iCloud, runs Tesseract OCR, extracts text, deduplicates with SHA-256 hashing, and stores everything in a searchable SQLite archive. Business cards get AI-powered field extraction.
The Result
Documents go from phone photo to searchable archive in under 5 minutes. Receipts feed into the purchase tracking pipeline. Business cards become a searchable contact database.
Tech Used
Python
Tesseract OCR
SQLite
Claude API
Click CLI
Want something like this for your business? Let's talk.