Akun.AI
An AI-assisted accounting platform designed to make bookkeeping and financial reporting more accessible to Indonesian SMEs.
Overview
Akun.AI is a pre-launch, AI-assisted accounting SaaS for Indonesian SMEs. It combines bookkeeping workflows, an accounting assistant, automated financial reporting, and a receipt-OCR prototype that still requires production validation.
Problem
Indonesian small and medium businesses struggle with bookkeeping complexity and lack accessible, AI-assisted accounting tools tailored to local requirements.
Target Users
Indonesian SME owners and operators
My Role
Solo product builder
Product planning, system architecture, frontend and backend development, accounting workflows, AI integration, reporting, and user experience.
My exact contribution
- Designed the accounting workspace architecture, including chart of accounts, ledger flows, reporting surfaces, and tenant-aware data boundaries.
- Built the full-stack SaaS flow across onboarding, dashboard, transactions, invoices, inventory, reports, AI assistant, and subscription surfaces.
- Integrated the AI assistant as a grounded finance helper that reads workspace context while deterministic validation still protects saved accounting actions.
Key Features
- Business onboarding and chart of accounts
- Double-entry accounting with validation
- Profit and loss reports and balance sheets
- CSV export and printable reports
- AI accounting assistant via OpenRouter
- Receipt OCR prototype for assisted transaction entry
- Team access and subscription management with Mayar
- Row-Level Security for data isolation
Feature status
Core bookkeeping and financial reports
Implemented across the current pre-launch workspace; production accounting and compliance behavior still need validation.
AI accounting assistant
Connected to workspace context with deterministic validation around saved accounting actions.
Receipt OCR
The extraction flow exists, but accuracy and failure handling are not yet production-validated.
Mayar billing
Mayar is the configured billing provider; end-to-end payment and webhook reliability are not claimed here.
AI System Notes
OpenRouter-configurable LLM layer with prototype OCR ingestion for receipt capture.
Supabase/PostgreSQL stores tenant-isolated business data; RLS boundaries protect workspace records before AI context is assembled.
Double-entry checks, category validation, and permission-aware queries keep financial answers tied to stored ledger data.
AI output is treated as advisory; accounting actions still pass through deterministic validation before being saved or reported.
Pre-launch system. Tax, OCR accuracy, and local compliance behavior still need deeper production validation.
Pipeline
- Business transactions, invoices, inventory changes, and prototype receipt-OCR outputs enter the ledger workspace.
- Structured transaction data is validated against chart-of-accounts rules before it reaches reports.
- The AI assistant answers from workspace context and summarizes financial state instead of acting as an unconstrained chatbot.
- Reports, CSV exports, and dashboard cards are generated from persisted accounting records.
Challenges & Trade-offs
- Designing accounting workflows that are accessible to non-accountants
- Implementing double-entry validation logic that catches common errors
- Building AI prompts that produce reliable, audit-ready accounting responses
Lessons Learned
- Accounting domain modeling requires deep understanding of Indonesian accounting standards
- AI integration for financial data needs careful grounding and validation
- Mayar billing integration requires explicit webhook and failure-path validation
Results
Pre-launch: built the core accounting workflow, financial reports, AI assistant, a receipt-OCR prototype, and Mayar subscription surfaces.
Proof Artifacts
