100% local · free
Questions on documents
Ask a question about internal procedures: the answer always cites its source document, or is not given at all.
Launch the demoORIA Lab · Automation
Pick a sample invoice or upload your own document: the text is read by OCR, key fields are extracted and amounts are cross-checked. Everything happens in your browser.
How it works
The Tesseract OCR engine, running in your browser, recognises the text and the position of every word. For a digital PDF, the text is read directly.
Rules locate the supplier, client, NIF and STAT numbers, dates, line items and totals from labels and page layout.
Sum of lines, subtotal + VAT, VAT rate: every inconsistency is flagged, never silently corrected.
You correct if needed, then export as CSV or JSON, formats an ERP can ingest directly.
In production, ORIA relies on stronger reading models (photos, complex tables, varied layouts), feeds the result into your ERP or CRM and routes uncertain cases to a review queue. The gain is measured before and after, on your own volumes.
Intelligent process automationOther demos
100% local · free
Ask a question about internal procedures: the answer always cites its source document, or is not given at all.
Launch the demo100% local · free
Spot, among 300 fictional customers, those slowly disengaging — earlier than a classic threshold rule.
Launch the demoNext step
A structured conversation with an AI architect — no commitment, no jargon.