Skip to content
YYefrixLab

Case study · AI & Automation

Taxonaut: accounting automation for Polish sole traders

Self-hosted auto-accountant for Polish JDG: invoices in, tax declarations out, with rules-as-data and tiered LLM processing.

Industry
Accounting & tax
Timeline
8 weeks, ongoing
Year
2026
Services
Product engineering, AI integration, Compliance research

The problem

A Polish sole trader (JDG) burns hours every month on the same loop: collect invoices, classify costs, compute ZUS and PIT advances, fill government forms, try not to miss a deadline. Accountants charge monthly retainers for what is, most months, deterministic paperwork. Off-the-shelf SaaS tools automate fragments, hold your data hostage, and still make you re-type numbers into government portals.

What we built

A self-hosted automation platform that treats accounting as a pipeline: documents and bank statements go in, ready-to-submit declarations and payment reminders come out.

Three design decisions carry the whole system:

  • Rules as data, not code. Polish tax rules change yearly. Rates, thresholds, form versions and computation rules live in versioned database tables with effective dates, so a rule change is a data migration, not a redeploy. The 2026 rates coexist with 2025 history cleanly.
  • Submit-as-is documents. Every government-bound artifact the system generates is validated against the current official schema. The hard rule: if it cannot be submitted without manual re-typing, it is a bug.
  • Tiered LLM processing. Bulk work like invoice field extraction runs on cheap fast models through a gateway. Critical-tier decisions, like ambiguous cost classification with tax consequences, are queued for a frontier model and processed asynchronously through a job queue, keeping quality where it matters and costs where they belong.

Architecture

FastAPI plus PostgreSQL (multi-tenant with row-level isolation), Celery workers and a scheduler for the monthly cycle, a Telegram bot for capture and reminders: photograph an invoice, get it parsed, classified and filed. A reminder service tracks statutory deadlines and nags with escalating urgency.

Why it matters

This is the pattern for a whole class of businesses: regulated, repetitive, deadline-driven paperwork where correctness is non-negotiable. Rules-as-data plus schema-validated outputs plus tiered AI is a template we can lift into any compliance-heavy domain.

Got a project that "just needs to ship"?

Tell me what you are building, what is blocking it, and when you need it live. You will get an honest answer about scope, cost, and timeline within 24 hours. No discovery-call theater.