Five AI features in an invoicing app, and the rules that keep them from touching the books

Slate, an invoicing and bookkeeping SaaS for Israeli businesses, has integrated five AI features—receipt scanning, a chat assistant, support reply drafter, natural language document creation, and column mapping for Excel imports—while adhering to strict legal constraints that require documents to be kept for seven years, numbered without gaps, and never edited after issue.

I build Slate, an invoicing and bookkeeping SaaS for Israeli businesses. Angular on the front, Express and Prisma on the back, Postgres underneath. The documents it issues are real fiscal records. Israeli law requires them kept for seven years, numbered without gaps, and never edited after issue. That constraint shaped every AI feature in the product. There are five of them today: receipt scanning photo of a receipt, out comes a filled expense form , a chat assistant that answers questions about your own books, a support reply drafter for the admin side, natural language document creation "quote for Dani, 3 consulting hours at 500" , and column mapping for Excel imports where every accountant's spreadsheet has different headers. You can see it here: https://www.slate.co.il/en/ features https://www.slate.co.il/en/ features