Invoice processing · Production

That Index Consulting automates financial document extraction and enhancement with Nanonets

The problem

That Index Consulting needed to onboard one of the UK's largest charities requiring indexing of hundreds of thousands of financial documents from global suppliers. Traditional OCR lacked the flexibility for data enhancement rules and the sheer volume made manual processing unfeasible—verification would have taken approximately three minutes per document.

First attempt

Traditional OCR required extensive training for new document formats, could not apply data-action rules, and was prone to misinterpreting UK PO codes—causing errors that would have required manual review of tens of thousands of invoices.

Workflow diagram · grounded in source
1
Document import via API
Trigger
All documents seamlessly entered the platform through an API call using the import block.
▾ source quote
“All documents seamlessly entered the platform through an API call using the import block”
2
OCR data extraction
Ai action
The OCR block efficiently extracted crucial information from invoices and credit notes in various formats.
▾ source quote
“The OCR block efficiently extracted crucial information from invoices and credit notes in various formats, achieving over 90% document extraction accuracy”
3
Data enhancement and validation
Validation
Over 100 data block steps facilitated operations including formatting dates, numbers, and currencies and matching information across two tables.
▾ source quote
“Data blocks proved effective in post-processing, incorporating checks and validation flags. Index utilized data blocks to format dates, numbers, and currencies and match information across two tables”
4
Export to MSSQL database
Output
Processed data was directly transferred to the MSSQL database in real-time.
▾ source quote
“Processed data was then directly transferred to their MSSQL database”
Reported outcome

Nanonets delivered over 90% document extraction accuracy with real-time export to the MSSQL database, and That Index can now process documents from different sources and formats while incorporating new data enhancement rules with minimal training.

Reported metrics
Document extraction accuracyover 90%
Manual verification time per document (avoided cost)approximately three minutes per document
Reported stack
NanonetsMSSQL
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://nanonets.com/customer-success-story/that-index-automates-data-extraction-and-enhancement
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Nanonets delivered over 90% document extraction accuracy with real-time export to the MSSQL database, and That Index can now process documents from different sources and formats while incorporating new data enhancemen…

What tools did this team use?

Nanonets, MSSQL.

What results were reported?

Document extraction accuracy: over 90%; Manual verification time per document (avoided cost): approximately three minutes per document (source-reported, not independently verified).

What failed first in this deployment?

Traditional OCR required extensive training for new document formats, could not apply data-action rules, and was prone to misinterpreting UK PO codes—causing errors that would have required manual review of tens of th…

How is this invoice processing AI workflow structured?

Document import via API → OCR data extraction → Data enhancement and validation → Export to MSSQL database.

Related invoice processing cases

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.

Browse the Invoice processing cases →