PLATFORM
Document infrastructure that you own
PDF, Excel, Word, PowerPoint, scans, images, emails, ZIP archives — feld.ai parses, classifies, and extracts. The foundation for AI agents, automated workflows, and structured data. Hosted on our own hardware in Austria. Not a single byte to Google, Amazon, or Microsoft.
Sovereign. Non-negotiable.
Your documents contain your business knowledge — customers, pricing, contracts, personnel files. With feld.ai, this data never leaves European jurisdiction. No US cloud. No telemetry export. No training of third-party models with your data.
Own hardware in Austria
Our GPU servers are located in Feldkirch, Vorarlberg. No AWS, no Azure, no GCP. Physical control over every rack.
Zero data flow to big tech
No API calls to OpenAI, Google, or Amazon. All models run locally. Your data is never used to train external AI.
Managed or on-premises
feld.ai cloud, deployment in your infrastructure, or full on-premises installation. You decide where your data lives.
GDPR native
Not a compliance patch after the fact — GDPR has been built into the architecture since day one. ISO 27001 in certification.
Parse everything that arrives
Businesses receive documents in dozens of formats. feld.ai understands them all — from handwritten scans to nested Excel spreadsheets to multi-page PowerPoint presentations.
PDF & scans
Digital PDFs, scanned documents, multi-page contracts. OCR and visual models combined.
Excel & spreadsheets
Structured and unstructured worksheets, multiple tabs, nested headers. No format assumptions.
Word & PowerPoint
Text documents, reports, presentations. Layout-aware extraction that understands structure.
Images & photos
Document photos, screenshots, whiteboard captures. Multimodal AI recognizes content even at low quality.
Emails & attachments
MSG, EML, and arbitrarily nested attachments. All incoming mail processed in a single step.
Multilingual
German, French, Italian, English, and more. Language detection is automatic, no manual tagging required.
Core capabilities
feld.ai is more than a parser. The platform is the foundation for AI-powered document workflows — from simple extraction to fully autonomous agents.
Classification
Automatically identify document types — invoice, contract, inquiry, notice. Trainable on your categories.
Extraction
Define fields, AI extracts. From invoice amounts to clauses in 200-page contracts.
Visual grounding
Every extracted field traceable to its source location in the document. Verifiable, not a black box.
Master data matching
Automatic matching with suppliers, IBANs, accounts, cost centers. Structured data, ready to use.
Agent foundation
The platform delivers structured data that AI agents consume directly. From mailroom to action — no manual step in between.
Semantic search & chat
Ask questions about your document archives in natural language. Answers with source references.
Correction UX
Human-in-the-loop with a fast validation interface. Every correction improves only your recognition — your data trains exclusively your model, never another customer's.
Redaction
Automatic redaction of sensitive information — names, IBANs, social security numbers.
From input to delivery
Integration
feld.ai integrates into your existing infrastructure — not the other way around.
REST API
Headless integration for all core steps — docs.feld.ai
Web app
User interface for end users, validation, and monitoring
Excel plugin
Direct connection to existing Excel workflows
Webhooks
Notification to third-party systems when processing completes
Why not AWS, Azure, or GCP?
Every document you process through US cloud services falls under the CLOUD Act. Your business data can be requested by US authorities without an EU court order. Your documents may be used to train the next model generation of a tech corporation.
feld.ai is the alternative: own models, own hardware, own jurisdiction. Document AI that belongs to you — not to a hyperscaler.
- No CLOUD Act — Austrian law, European jurisdiction
- No model training with your data — contractually guaranteed
- No vendor lock-in — standard APIs, data export anytime
- No telemetry — no tracking, no phoning home
Model architecture — three tiers, all local
feld.ai runs all AI models on its own GPU servers in Feldkirch. Zero API calls to OpenAI, Anthropic, Google Vertex, or Azure OpenAI. Three tiers:
Large open-weights models
For document understanding, chat, and reasoning. Model families under evaluation: DeepSeek, GLM, Qwen, Llama, Mistral, Kimi, Gemma, Phi. Downloaded and run locally.
Proprietary small models
Built from the ground up by the feld.ai team. Graph-based models for Excel parsing: table detection, layout understanding, cell classification, mapping to ontologies.
Fine-tuned specialist models
Fine-tuned and re-implemented models for specific document types. Optimized for high precision and throughput in production.
All three tiers run air-gapped on own servers. No model has internet access. No model sends telemetry. Full disclosure: Sovereignty.