Endura AI — founder
Multi-Agent Financial Automation
Agentic bookkeeping and reconciliation for chartered accountants
7d → 4h month-end reconciliation
Built with
PythonLangGraphDSPyPydanticGeminiRAG
- The problem
- Month-end close for a chartered accountant is days of moving data between Tally, bank statements, and QuickBooks, categorizing transactions by hand. The work is high-volume, rule-shaped, and unforgiving of errors — a bad categorization is an audit finding, not a bug report.
- My role
- Founder and sole engineer. Architecture, agents, integrations, and the extraction pipeline.
- Approach
- Structured extraction over free-form generation. Documents parse through Gemini, but every output is forced through DSPy and Pydantic schemas, so an unparseable record fails loudly instead of arriving plausible and wrong. Retrieval is tenant-isolated at client, company, and folder scope — slower to build than a shared index, but the only version defensible for accounting data.
- Outcome
- The reconciliation agent ingested 10,000+ bank transactions with confidence-scored auto-categorization, collapsing manual month-end reconciliation from 7–8 days to 3–4 hours.
What I built
- A multi-agent system in LangGraph that automates bookkeeping and the month-end close for chartered accountants, connected directly to Tally.
- A reconciliation agent that syncs with QuickBooks both ways and categorizes bank transactions with a confidence score.
- Safe extraction. Documents are parsed with Gemini and checked against strict schemas, and each client’s data is kept fully separate.
Questions about this one? Email me, or ask my AI assistant.