In2 Project Management automates invoice validation for a water corporation using Nanonets
The client, a water corporation spending circa $10 million AUD per year on external maintenance, needed to audit invoice accuracy across 72 invoice formats and 3500 line items per month — a scale that exceeded what manual spreadsheet review could handle, leaving discrepancies undetected.
The team's manual approach of collecting invoices and building spreadsheets could not scale to the volume and variety of invoice formats, leaving verification gaps and discrepancies unaddressed.
Nanonets enabled identification of a $30k discrepancy between SAP Ariba portal expenses and extracted invoice data, surfaced cost inconsistencies across suppliers for the same equipment, and validated supplier ABN numbers — described as fundamental in saving cost.
Frequently asked questions
What did this team achieve with this AI workflow?
Nanonets enabled identification of a $30k discrepancy between SAP Ariba portal expenses and extracted invoice data, surfaced cost inconsistencies across suppliers for the same equipment, and validated supplier ABN num…
What tools did this team use?
Nanonets, Nanonets Pre-trained Invoice Extractor, ABN lookup web services, SAP Ariba, Sharepoint, SQL Database, Power BI.
What results were reported?
discrepancy identified in SAP Ariba vs extracted invoice data: $30k; Annual client maintenance spend: circa $10 million AUD / year; Cost saving impact: very fundamental in saving cost (source-reported, not independently verified).
What failed first in this deployment?
The team's manual approach of collecting invoices and building spreadsheets could not scale to the volume and variety of invoice formats, leaving verification gaps and discrepancies unaddressed.
How is this invoice processing AI workflow structured?
Invoice intake from multiple sources → Real-time invoice data extraction → Route to SQL database → Validation against spend management system → Live ABN company validation → Power BI visualisation output.