Automation Engineering student building AI and robotics systems.
Interested in reinforcement learning, physical AI and systems that interact with the real world.
Bremen
Since October 2024 I've been studying Automation Engineering in a dual work-study program. I learn the theory at Hochschule Bremen and spend my practical phases at KUKA.
I use coding agents like Claude Code and Codex heavily for implementation. I focus on the engineering around it: requirements, system design and architecture, experiments, debugging, integration, and validating whether the system actually works.
My current project. I'm training the arm on physical AI tasks: computer vision and path planning, built with ROS 2, MoveIt and RViz2. That includes getting from the real arm into simulation and back again: Real2Sim and Sim2Real.
I'm building a Sesame Robot and training it with reinforcement learning. The double pendulum at the top of this page was the start. Now it moves from simulation to a real robot. This keeps running alongside the robot arm.
An assistant that watches an expert work, listens to their narration and asks about decisions at natural pauses. The session becomes a Work Map of steps, rules and reasons. A new colleague then practices with it, and mistakes get caught before saving. Screenshots are OCR'd and redacted right in the browser. Started at Hack-Nation 7.
Capture
Teach
| Screenshot pipeline (sparse screen) | 378 ms end to end |
|---|---|
| Screenshot pipeline (dense screen) | 1,512 ms end to end |
| Capture | every 2 s, full-resolution frame |
TypeScript · React · TanStack Start · Convex · Claude · ElevenLabs · Tesseract.js
A Dynamic Island for the Windows desktop. A small capsule at the top of the screen shows my Claude Code and Codex usage, music, a focus timer, meetings and system health. It reads the tools' local logs, sends nothing to the cloud and idles at 55 MB and 0.03 % of one CPU core. The code is open source.
Data
Display
| Idle, compact, 60 s window | 55 MB working set, 16 ms CPU (0.03 % of one core) |
|---|---|
| Warm start | 47 ms (only the changed transcript is re-read) |
| Tests | 382 unit tests |
C# · .NET 10 · WinUI 3 · SQLite · xUnit
Started at the Smart Region Hackathon Offenburg. A platform where utilities, municipalities and contractors coordinate roadworks. It shows conflicts before the same street gets dug up twice. After the hackathon I kept building: an AI reads requests from PDFs or free text and pre-fills the form, approvals work through a link without an account, plus a map and a landing page.
Requests
Next.js · TypeScript · PostgreSQL · Drizzle · MapLibre · LLM via OpenRouter
Three automations for small businesses. Extract invoices from PDFs and check that the line items actually add up to the total. Sort incoming emails and prepare replies as drafts, never send them automatically. Track prices and stock in online shops that have no API. When the AI isn't sure, a human decides.
Invoices
n8n · LLM via HTTP · Google Sheets · Airtable · Slack · Gmail
October 2026
We sorted waste with a robot arm, using 6D pose estimation and machine learning.
October 2026
May 2026
This is where Baulify started.
Anthropic
Google Cloud
Grouped by how I've actually used them.
A hackathon write-up: camera-to-robot calibration with AprilTags from 20 poses, grasping with ROS 2 and MoveIt, sorting objects by their height, and the computer vision part that did not make it into the demo.
ROS 2 · MoveIt · Python · AprilTag · Claude Code
A native Windows status capsule built with .NET 10 and WinUI 3: a fixed-size transparent window, spring morphs, event-driven providers that read local usage logs, and an idle cost measured in milliseconds.
C# · .NET 10 · WinUI 3 · Windows App SDK · SQLite · LibreHardwareMonitor · xUnit · Inno Setup
A hackathon project that records an expert's workflow, asks for the reasoning behind decisions and turns it into a Work Map, with a guided practice mode that catches mistakes before they are saved.
TypeScript · React 19 · TanStack Start · Convex · Anthropic · ElevenLabs · Tesseract.js · Railway
