feld.ai
“Platform and API for document-heavy workflows: invoice intake, digital mailrooms, case-file work, reference-data matching, document generation and redaction.”
feld.ai GmbH
Feld.ai: “feld.ai baut und betreibt KI-Agenten für dokumentenreiche Abläufe, darunter Rechnungseingang, digitaler Posteingang und Aktenarbeit. Der Betrieb erfolgt in Österreich oder in der Umgebung des Kunden.”
Products & services
Questions & answers
Why do my AI agents cost so much in tokens?
“Generalist LLM agents re-read large contexts with the most expensive model on every run — every document, every intermediate output, every retry costs tokens. In long value chains these costs multiply per step. For structurable high-volume processes that is the wrong tool: specialized document AI processes the same documents at measured processing costs.”
How do I calculate the ROI of a document process?
“Cost per result instead of cost per token: (unit cost per document + cost of manual rework) × volume, compared with your current process costs. What matters are measured model costs for your document mix and precision that actually reduces rework. feld.ai runs this calculation with you in the first call, based on your real document mix.”
What does processing cost per document?
“feld.ai costs from €75 net per active user per month (Basic); Team €199, Professional €400. Model consumption is billed additionally by usage. Setup, integration and deployment model are stated in the quote before production; model consumption is charged at agreed rates.”
How many document types can the system distinguish?
“There is no fixed upper limit. In practice, our models distinguish between 5 and over 80 classes — depending on the use case. New classes can be trained with just a few example documents.”
How much effort is the initial training?
“For most classes, 20 to 50 example documents per category are sufficient. For very specific document types, even fewer are often enough. Training typically takes just a few hours.”
Does classification support multiple languages?
“Yes. Our models work language-independently based on visual and textual features. German, English, French and other European languages are supported without separate training.”
How accurate is the classification?
“In production environments we typically achieve over 95% accuracy. With extreme class imbalance (e.g. 99% invoices, 1% special cases), feld.ai employs specialised techniques to reliably identify rare classes.”
How does integration with existing systems work?
“feld.ai provides a REST API for all classification steps. Webhooks that notify your system when processing completes are coming in 2026. Integration with existing DMS, ERP or workflow systems is possible via standard interfaces.”
Which file formats are supported?
“feld.ai processes PDF, TIFF, JPEG, PNG and common Office formats (DOCX, XLSX). Multi-page and nested PDFs with attachments are also correctly resolved and structured.”
Can feld.ai recognise handwriting?
“Yes. Our multimodal models recognise printed text and handwriting equally well. Quality depends on legibility, but even difficult handwriting is captured significantly better than with traditional OCR.”
What is the difference between structured and unstructured documents?
“Structured documents (e.g. forms) have fixed fields at defined positions. Unstructured documents (e.g. letters, reports) contain relevant information at varying locations. feld.ai processes both types — without templates.”
Is there an API for integration?
“Yes. A REST API enables full integration into your existing workflows. Documents can be uploaded and results retrieved as JSON via the API. Webhooks that notify your system when processing completes are coming in 2026.”
How is data protection ensured?
“All data is processed on our own hardware in Austria. No US cloud provider is used. Customer data is stored in isolation and trains only the customer's own model.”
Company details
Data formats & record details
Download this profile and inspect its supporting evidence.
- Entity ID
- urn:readyscan:entity:feld-ai-gmbh-q140070925
- Material fingerprint
- fnv1a64:75634aaa59766922
- Entity revision
- fnv1a64:6c2d9f1788a9c7f7
- Published
- 2026-10-18
- Modified
- 2026-10-18
- Source summary
- Feld.ai: “feld.ai baut und betreibt KI-Agenten für dokumentenreiche Abläufe, darunter Rechnungseingang, digitaler Posteingang und Aktenarbeit. Der Betrieb erfolgt in Österreich oder in der Umgebung des Kunden.”