Responsibly implemented
Guardrails, source citations and transparency are part of it: chatbots are labelled as AI (EU AI Act), data flows are traceable, and sensitive data stays in-house where necessary.
AI Agents & Automation
We build AI assistants, knowledge bots and automations that are tested on your data – with source citations, an eye on data protection and an honest assessment of strengths and limits.
From knowledge research to process automation – matched to your infrastructure.
Guardrails, source citations and transparency are part of it: chatbots are labelled as AI (EU AI Act), data flows are traceable, and sensitive data stays in-house where necessary.
We start with a working MVP as a proof of value – with testing on real user questions and an honest recommendation on going into production.
Chatbot & Voicebot
Chatbots, voicebots and knowledge bots can be added on this basis. They are disabled by default; no data is sent to third parties until you consciously start a function and consent.
Answers questions based on your content (RAG) – labelled as AI (EU AI Act).
Phone/voice assistance for recurring matters – with a recording and AI notice.
Before activation we clarify data flows, data processing agreements, third-country questions and the EU AI Act labelling obligation (from 2 Aug 2026). Details in the integration concept.
Matching packages
Turn a good idea into a ready-to-build concept: data check, solution sketch, effort/value, go/no-go.
2–3 weeksA structured, responsible Copilot rollout – from readiness and use cases to team enablement.
3–6 weeksA working assistant, tested on your data – with source citations, data protection and an honest evaluation.
4–8 weeksCloses the gap from pilot to production – hands-on, with success criteria and user enablement.
6–12 weeksFAQ
We rely on RAG with source citations, guardrails and a quality test with real questions – and name the limits openly.
Data protection is part of the design. For sensitive data, local/on-prem options are possible; data flows are documented.
We build an MVP on your data – as a robust proof of value.