AI agents for your company, from a company that runs on them.
We build and run our own company with AI agents. For yours, we start with one process, build the agent on your systems, and measure it against how the work was done before.
Where agents fit
Good first candidates are frequent, rule-bound tasks where a person checks the result today anyway.
Software engineering
The backlog your developers never reach: tests, migrations, internal tools and integrations, written by agents and reviewed by your team.
Operations and monitoring
Systems watched around the clock, alerts turned into tickets, routine fixes prepared for a person to approve.
Documents in, data out
Tenders, specifications, supplier offers and delivery notes read, sorted and entered where they belong.
Quotes and reports
First drafts of offers from a bill of quantities, and monthly or portfolio reports assembled from the systems where the data already lives.
How a project runs
- 1
Choose one process
With the people who do the work today, we pick one process and agree how it will be judged: time spent, error rate, throughput, or whatever the work is measured by now.
- 2
Pilot at a fixed price
We build the agent on your systems and run it alongside the current process for a few weeks, on the same cases, so the two can be compared.
- 3
Run or hand over
If the pilot holds up, the agent goes into daily use. We keep running and improving it, or hand it over to your team with code and documentation.
Safeguards
The rules we agree with you before an agent touches your systems.
People stay accountable
Agents work inside scopes you approve in writing. Releases, irreversible changes and anything touching personal data need a named person.
Your data stays yours
We use only model providers you approve, under a data-processing agreement, or keep the data entirely in-house.
Every step is traceable
Each task is a ticket and each change a reviewed pull request, so you can see what an agent did and why.
How our own company runs
- 1
Agents do the work
AI agents write the code, run the tests, watch our systems and draft what needs deciding. Each works in a standing role, such as operations, business or this website, with a shared memory of what was decided and why.
- 2
Tested and reviewed
Our rules require each change to be tested on the scenario it touches, in a real browser for anything users see, and reviewed by an AI model from a different provider where the risk calls for it. The agents then merge into our working branch and run staging themselves.
- 3
Production, within limits
In production, agents act on their own under a standing permission from us, for example to fix an incident while they watch the result. Rewriting or deleting user data, credentials and anything sent outside need a named approval from one of us.
Mistakes become lessons
When an agent gets something wrong, or one of us corrects it, the agent writes down what happened and what would have prevented it. The lesson reaches every other agent, and where it can, it becomes an automatic check instead of a reminder. The agents get more experienced as a team, without anyone retraining them.
Standing agent sessions
Long-running agent sessions on two always-on machines, each in a fixed role: operations, business, a research engagement, this website. They message each other directly instead of rebuilding what another one owns.
A shared memory
One versioned memory store per project, synced across machines every 20 minutes, so every session starts with the same context. Facts carry a lease and are checked again when it runs out; nothing is deleted silently, so a correction is never lost.
Tickets and a board
Every request becomes a ticket with a status, and a board shows which session is doing what. Each session starts from the same operating manual and the open tickets.
Orchestrated teams
For larger work, an orchestrating agent plans the phases, sends out a team of agents in parallel and has a critic check what comes back before anything is merged or sent.
Working with us
- Who you work with
- The people who build the agent, from the first conversation to daily use.
- Languages
- German and English.
- Where
- Munich and Berlin. On site when it helps, otherwise remote.
Have a process in mind?
Write to [email protected]. A few lines about it are enough to start. We reply in German or English.