Services
From the first assessment to ongoing operation. Here is what we build and how we go about it.
Services
We do not build models. We bring proven AI to the places in your processes where it measurably takes work off your team.
An assistant that knows your own documents and answers questions from them, with a source reference, so every answer stays verifiable.
A fit if
Your knowledge lives in documents and nobody finds it fast enough.
Recurring work runs by itself. We build on open automation platforms, hosted on your servers or on ours inside the EU.
A fit if
Your team copies data back and forth between programs.
AI built in where your software already runs, as an interface, an extension, or an application of its own.
A fit if
You have a platform and want AI usable inside it.
How it works
No annual contract, no consulting package bought on faith. Every step produces a result, and you decide whether the next one happens.
30 minutes
We listen, ask questions and tell you honestly whether AI is worth it for your case, including when the answer is no.
You get
1 to 2 weeks
We look at your processes and data properly and prioritise what delivers the most value.
You get
4 to 8 weeks
One use case goes live, not as a demo, but in real everyday operation.
You get
monthly, cancellable
We keep the solution running and add further processes once the first one has proven itself.
You get
We quote prices once we understand your case. A list price would only be a guess. After the consultation you receive a concrete fixed price offer.
Data protection & regulation
Data protection is the most common reason AI projects never start. So we settle where your data lives and who can see it before the first line of code.
Anything that leaves the company or costs money is approved by a human. No unsupervised automation.
The transparency obligations of the AI Act have applied since 2 August 2026. For most companies the effort is manageable, you just have to know about it.
We are engineers and not lawyers. We implement and document the technical requirements. The legal assessment stays with your legal advisors.
For technical readers
For anyone who wants the detail. This is how a request moves through the system, and where a human steps in.
Break down the task
A request is split into traceable individual steps.
Use tools
The agent reads from your systems and writes back under control.
Ground the answer
Every statement is tied to a source in your data.
Ask for approval
A human decides before anything leaves the company.
Keep a log
Every step is recorded and can be audited later.
Stay within limits
Permissions and data access are scoped tightly per use case.
An assistant that cannot say where an answer came from is useless inside a company. So every answer is tied to a source, every step is logged, and every action with outside effect is approved by a person. That takes a little more effort, and it makes the solution auditable.
How a request flows
Common questions
It depends on the use case, which is why we publish no list prices. The sequence is always the same. After the free consultation you get a rough order of magnitude, after the potential check a binding fixed price offer. You never sign anything whose price you did not know in advance.
The potential check takes one to two weeks. A pilot then goes live in four to eight weeks. So within roughly two months you have something running in real daily operation.
Then you can. Code, configuration and documentation belong to you and are handed over. We work with open, widely used tools so you are not dependent on us.
That is why we do not build free talking assistants. Ours answer only from documents you have approved and cite a source for every statement. If the system finds no basis, it says so instead of guessing.
