Finance AI Hack
Local-first invoice reconciliation and anomaly detection on a Cognee knowledge graph. No data leaves the machine.
The Problem
Finance ops teams manually reconcile invoices, catch anomalies by scanning spreadsheets, and miss patterns because the volume is inhuman. Sending financial data to cloud AI services is a non-starter for most companies — compliance, security, trust.
The Approach
Local-first architecture using Ollama for on-device inference and Cognee for knowledge graph construction. Four agents: Reconciliation Dashboard matches invoices and flags mismatches. Invoice Processing Agent normalizes vendor info and risk scores. Anomaly Detection prioritizes irregularities. Missing Invoice Flagging spots gaps by vendor and time period.
The design bet: a small local model on a well-structured knowledge graph outperforms a larger cloud model on raw text for domain-specific finance tasks.
The Result
Fully functional hackathon project. Zero data leaves the machine — model weights, graph DB, and vector store all run locally. Four distinct finance ops capabilities in a single Streamlit interface.
My Role
Co-creator with Anton Iemelianov. Built agent prompts and output parsing, integrated the Cognee knowledge graph, and made the product call to go local-first over cloud-first.