Turn any document into
structured data.

Teach Harold how your documents work.

Out of the box Harold extracts standard header information from common business documents such as invoices and purchase orders.

But every business is different. With DocuTrain you can train Harold to understand any document layout — including line items, tables, and custom fields specific to your suppliers.

We do not charge more for line items or complex documents.

Once trained, Harold remembers the structure and applies it automatically.

Turn messy documents into structured data.

Once trained, Harold reads each document and extracts the data automatically — supplier names, totals, references, dates, and line items.

No manual data entry.

Just clean structured data ready for the next step.

Extraction is only half the job. Harold can also apply rules to the extracted data.

For example a supplier might appear on documents as DAVIDBRENT but your internal system expects the supplier ID DB00001. Create a rule once and Harold will automatically output the correct supplier ID every time.

Rules can also handle:

• ·Supplier ID matching
• ·VAT or tax validation
• ·Date formatting
• ·Data cleanup
• ·Field standardisation

Once the rules are set Harold applies them automatically in the background.

Once documents are extracted and rules are applied Harold exports clean structured data ready for your systems.

Export options include CSV and Excel.