AI Engineer · Product Builder · Berlin / remote

I build tools that make complex things clearer, calmer, and more useful.

Across healthcare, legal research, public services and agent workflows, I turn complicated problems into practical products people can understand, test and use.

Explore CareOS ↗See selected work ↓Download CV ↓

Why I build

I keep noticing systems people have learned to tolerate.

Bureaucracy that takes weeks. Rights that are hard to understand. Important information scattered across institutions. Software that creates work instead of removing it.

My instinct is usually the same: Why does this have to be so complicated? What would the better version look like?

So I build a small version of the answer, put it in front of reality, and learn where it breaks.

Selected work

Four projects that best show how I think and build.

Each has a different maturity level. I would rather show the real state than make a prototype sound like a finished company.

Healthcare AISynthetic reference build

CareOS

Why it exists Clinicians should not spend scarce attention reconstructing information a hospital already has.

Bring source-linked clinical context together while keeping uncertainty, permissions and human judgement explicit.

Synthetic KIS/LIS/FHIR/document workflows → patient-bound context → contradiction handling → bounded agent drafts → failure replay → measurable workflow study. Real hospital evidence is deliberately still open.

FHIR / ISiKagent containmentworkflow evaluation

Open work sample ↗GitHub ↗

Legal researchLive pilot

GitLaw

Why it exists Rights are much less useful when understanding them requires legal expertise.

Find the law behind a real-life problem without hiding the source trail.

Plain-language questions → relevant German federal law → inspectable source passages → visible uncertainty. Real user-found retrieval failures are turned into regression tests.

5,936 lawsMietrecht pilotreal-user testing underway

Try it ↗GitHub ↗

Reliable AI workEngineering prototype

Digital Worker Factory

Why it exists AI should remove repetitive work without quietly removing accountability.

Make AI workers show evidence, expose failure and ask before consequential actions.

The current reliability suite is synthetic. The next meaningful proof is one real office workflow running in shadow mode with human corrections measured.

approval gatesaudit & replayreal workflow next

Open technical demo ↗GitHub ↗

Public administrationGovTech prototype

PrüfPilot

Why it exists Skilled reviewers should spend their attention on judgement and exceptions, not reconstructing information from documents.

Help reviewers see what a document proves, what is missing and what needs a human decision.

Synthetic cases demonstrate the workflow; the document-intake core is working. The next proof is an institution or domain expert using their own documents.

document intakeversioned ruleshuman review

Open prototype ↗GitHub ↗

What I focus on

Useful systems, not AI for its own sake.

Make complexity understandable.

Turn rules, documents and messy workflows into something a person can actually reason about.

Build the smallest useful version.

Enough product to let someone complete the real task — not just watch a polished demo.

Keep humans in control.

Especially when a wrong answer could affect rights, money, safety or consequential decisions.

Improve from real use.

User-found failures should become tests, product changes and measurable evidence.

Areas I work across

Different surfaces. A consistent reason for building.

The projects look different, but each begins with a human question: what friction can disappear, what becomes understandable, or what becomes more joyful?

Civic & legal AI

Rights and public services only create value when people can actually find, understand and use them.

GitLaw Citizen Agents SafeVoice OpenLeistung

Reliable AI systems

Automation should reduce repetitive work without hiding uncertainty, evidence or responsibility.

CareOS Worker Factory demo Agent Loop Lab

Human systems

Technology can help people understand themselves and one another, not only optimise their output.

Empathly Path to Peace

Play & worlds

Not everything worth building needs to save time. Some things should create joy, connection and wonder.

BlaKeks World · privateTiny Tactics · privateTiến Lên

Product experiments

A good product earns attention by being useful, delightful or valuable enough that someone wants to return.

Atelier Engine LuckLab

See the broader project archive →

How I work

Understand. Build. Test. Learn.

I do not start with the model. I start with the person, the problem and what a good outcome should feel like.

Understand

Who is this for? What is hard today? What would make the experience genuinely better?

Clarify

What do we know, what is missing, which rules matter and what should remain a human decision?

Build

Connect data, AI and interface into the smallest version someone can actually use.

Test

Put it in front of real and simulated cases, capture failures and turn corrections into better behaviour.

North star

Technology should return human attention to things worthy of being human.

A parent should not spend it deciphering benefits. A caseworker should not spend it copying between documents. A nurse should not spend it reconstructing information a system already knows. And sometimes, attention should simply be free for play.

If you’re hiring

Start with the proof closest to your problem.

I’m looking for AI Engineer / Applied AI roles where product judgement matters as much as making the system work.

Healthcare AICareOS / Recare work sampleclinical context + safe agents ↗LegalTechGitLawresearch + source grounding ↗GovTech / administrationPrüfPilotdocuments + review workflow ↗Agent systemsDigital Worker Factorytechnical demo + reliability ↗

About

Build environments where people can understand, act and thrive.

I’m an AI engineer with a founder and operations background. I like turning messy systems into clear tools, shipping quickly, and then finding out where reality disagrees with the demo.

I care most about work that reduces friction, increases understanding and gives people more room to make good decisions. I also build games and small product experiments because usefulness is not the only thing that matters — delight matters too.

Culture & inspirations →Read web CV →LinkedIn ↗

Next team

Bring me the messy problem.

If you’re building something difficult, useful and genuinely meant for people, I’d like to hear about it.

Email Michael CV EN ↓CV DE ↓