SOLUTIONS

Four AI patterns and one WiFi specialty.

Each pattern grew in real operations — and is shaped so it transfers to comparable companies without starting from scratch each time.

Website content → vector database → MCP tools → swappable LLM → streaming sidebar.

AI inquiry on your website

AI search grounded in your own content — no hallucinated answers, just statements with source attribution.
Read more
Receipt → vision LLM with context prompt → validation table → human approval → export to your target system.

Invoice processing with vision AI

Incoming receipts land structured in accounting — with a human-in-the-loop for edge cases instead of blind trust in the model.
Read more
Mailbox → sender filter → attachment or content → AI understanding where needed → naming → structured filing → marking as done.

Email & newsletter workflows

Routine emails process themselves: newsletters into the knowledge archive, invoices into the accounting folder, spam into the bin — all rule-based, with AI understanding only where genuinely needed.
Read more
Source content → AI processing in phases → human review → CMS integration. DE/EN parity without a parallel writing team.

Bilingual content pipelines

Content is maintained in both languages — without needing a parallel translator team on standby. The editor keeps editorial control.
Read more

Alongside — as a twenty-year-deep specialty

SPECIAL DOMAIN

Captive portal → RADIUS stack → authentication → payment integration → multi-site aggregation. Specialist area, twenty years deep.

WiFi platforms & captive portals

WiFi authentication for train stations, ports and city centres — from the captive portal UI to RADIUS aggregation across multiple sites.
Read more

Looking for more?

We also build a platform.

When several of these patterns should become one workplace over time — chat, knowledge base, importers and agents under one surface — that platform is CompanyWizard.

See CompanyWizard

What sets us apart

Four signatures we do not negotiate.

Swappable language model

Anthropic, OpenAI, Mistral, or local via Ollama — a configuration choice, not a code rebuild. Your model strategy stays free.
EU hosting, on-premise possible

Data sovereignty in practice: personal-data pseudonymisation, local models for sensitive fields, no cloud sync for sensitive data.
Dry-run before live-run

Before anything is automatically written, you see the full plan. Only when you're satisfied does it run for real.
What we deliberately don't automate

In every solution we document which decisions stay with humans by design — and why. Honesty as the foundation of trust.