DE EN

Solutions

Data Extraction from Records

Thousands of records scanned — but sitting as a PDF graveyard in the DMS. No indexing, no structure, no value.

The Solution

feld.ai extracts metadata and key information from record archives. Hierarchical structuring, summaries, semantic search.

How It Works

1. Ingest file archives — PDF archives, DMS exports or scan folders are fully ingested. feld.ai also handles handwritten and poorly scanned documents.

2. Detect structure — AI detects the hierarchical structure of each file — cover page, sub-chapters, attachments — and arranges pages thematically and chronologically.

3. Extract metadata and key information — Relevant fields (reference numbers, dates, parties, deadlines, amounts) are automatically extracted and provided as structured data.

4. Make searchable — Extracted data is indexed. Semantic search and optional AI chat provide access to knowledge previously locked inside PDFs.

Large Data Volumes

Processing the backlog — large volumes at once

Hierarchical Structuring

Chronological and thematic

Knowledge Base

Linking with legal requirements in context

Searchable Articles

Document archives become searchable articles

Related Solutions

Document Chat — Ask questions about your documents and get instant answers.

Compliance Documentation — Automatically check regulatory requirements.

Industry Solution: Reinsurance — Process bordereaux and treaty data.

Frequently Asked Questions

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 notify when processing completes.

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.

Request a demo for data extraction

Request Demo