Akun.AI
An AI-assisted accounting platform designed to make bookkeeping and financial reporting more accessible to Indonesian SMEs.
Overview
Akun.AI is an AI-assisted accounting SaaS built for Indonesian SMEs. It combines modern bookkeeping with AI capabilities including an accounting assistant, receipt OCR, and automated financial reporting.
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.
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 for automatic transaction entry
- Team access and subscription management with Stripe
- Row-Level Security for data isolation
AI System Notes
OpenRouter-configurable LLM layer with planned 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 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
- Stripe integration with Indonesian business use cases has unique considerations
Results
Pre-launch: built full accounting workflow including chart of accounts, double-entry validation, financial reports, AI assistant, receipt OCR, and subscription management.
Proof Artifacts
