AI agents that know your business.

Web chat, WhatsApp, phone, email — AI agents that work on your real data, not on a generic LLM playground. With a RAG pipeline on your content, MCP tooling for your applications and gold-standard evaluation datasets against hallucinations. GDPR-compliant, model-vendor agnostic, hosted in Germany.

Three ways to introduce AI in your setup.

Office Agent Suite

For anyone whose biggest lever sits in office day-to-day work: pre-classify the inbox, prepare quotes, make knowledge from SharePoint and Confluence available. Web chat as the standard channel, optional WhatsApp and phone via business-agent-pro.

TYPO3 Business Agent

For platforms running TYPO3 as a CMS: a conversational agent directly in the frontend that knows your content — with access-class routing (Public, Partner, Internal, Admin), MCP tool integration into the backend, and an embeddable chat widget. Runs on our open-source extension business-agent.

AI integration into your existing IT

For existing systems that aren't TYPO3: SAP, MS 365, your own ERP or CRM applications, ALB stacks. We build RAG pipelines on your real data and MCP servers to your applications — without you having to rethink everything.

Model-vendor agnostic. RAG-validated. GDPR-compliant.

We don't tie you to one AI vendor. The architecture allows model swaps at any time — OpenAI, Anthropic, Mistral, self-hosted. Gold-standard evaluation datasets run alongside every model or prompt update, with a clear pass/fail threshold. Hosting in Germany, model inference in an EU region if you want it. If you buy in Germany, something runs here too.

How we get to a productive agent together

1. Discovery

1–2 weeks. Use-case workshop, data-source inventory, risk assessment, channel choice. Outcome: a prioritised use case and an architecture sketch.

2. Pilot

4–6 weeks. First RAG pipeline on a real data slice, MCP server connection to the prioritised application, evaluation dataset with gold-standard answers. You see productive answer quality on your content, not in a demo.

3. Rollout

4–8 weeks. Extension to further data sources, additional use cases, audience integration via web chat or — if needed — WhatsApp, phone, email via business-agent-pro. Includes audit log and permission model.

4. Operate

Continuously. Model updates run automatically through the evaluation pipeline. Data sources update incrementally. Quarterly use-case review with your team — what runs, what's coming next, what gets switched off.

Pricing range — AI Agent as a Service.

Range: €1,900–€4,900/month (≈ £1,635–£4,215 / $2,050–$5,290) · minimum term 12 months

Included in the price: RAG pipeline, MCP tooling, eval framework, and one productive channel (web chat). The exact price comes out of data-source complexity, number of use cases, and eval depth — set in the 30-minute first call.

Additional channels (WhatsApp, phone, email, social) via business-agent-pro require a licence — pricing on request. Third-party costs (model API, WhatsApp Business API) separate. As of Q2 2026.

What we don't do.

We don't build full-autonomy agents that place orders or make legally binding statements without an audit trail. We don't build chatbots as a marketing gadget with three pre-prepared answers. And we don't swap out working existing systems for an AI stack just because AI happens to be loud right now.

If that's exactly what you want, we're the wrong address. If you want to introduce AI as a tool that gives your team time back and stays traceable — then we're a good match.

Brownfield. Model-vendor agnostic. With an evaluation pipeline. GDPR-compliant.

Which use case is worth tackling first?

In 30 minutes we'll work out where AI in your setup has the biggest lever — office routine, CMS workflow or customer touchpoint. With an honest recommendation if your next step looks more like an internal pilot than a finished product. Free of charge, no obligation.