How can we create a (mostly) safe environment for running LLM-based code review? Amidst the hype around AI, security concerns may easily be forgotten. The aim of this POC project was to build a secure context in which LLMs can be used for code reviews. The goal was to be able to review untrusted but proprietary code. The main concerns were: Prompt injection and data or code exfiltration.
The result was a pull request review orchestrator with a small Express/SQLite control UI. For each review it creates an isolated Docker setup with separate containers for code review, infrastructure access via MCP and limited web access via proxy.
Full-stack web application for digital workshop facilitation and business strategy development. Features real-time collaborative whiteboard with canvases for SWOT analysis, value proposition design, design thinking workshops, and business model development. Includes guided workshop templates, real-time cursor tracking, user presence indicators, and integrated tools for brainstorming, clustering, and presentation. Built with React frontend and NestJS backend with WebSocket support for realtime team collaboration.
I build this project as part of a 4 people startup team, in which I handled most of the tech work and coordinated one remote developer. The other team members focused on business development, marketing and customer acquisition. Unfortunately we could not acquire enough customers to make the project sustainable in the long run, so we had to discontinue it in 2022.
Digital patient questionnaire system for medical practices developed during EXXETA LVLX Summercamp. Features end-to-end encrypted patient data collection with dynamic form generation, digital signatures, PDF generation, and secure certificate-based data transmission. The platform includes a Laravel backend API with user authentication and an Angular frontend with responsive form components for medical intake forms, consent forms, and patient history collection. Built as a prototype to modernize paper-based patient intake processes in medical practices. The prototype was deployed on Azure and has been successfully tested in a real-world medical practice setting in Berlin.
Collaborative jukebox for Spotify: guests search and vote, and the top‑voted track is auto‑queued a few seconds before the current one ends. QR codes planted around our flat during parties ended the music DJ duties for good. You don't like this track? Search and vote for the next one!
Web-based enterprise application for the meat producing industry (Schlachthof). Based on the same self-developed platform used for the courier logistics application, featuring integration of domain-specific import and export interfaces (e.g. EDIFACT) and generation of domain-specific PDF documents to fulfill regulatory requirements applicable to the meat processing industry in Germany. As of 2025, this application is still in active use.
Web-based enterprise application for courier logistics with carrier interfaces for 'derKurier', FedEx and GLS. Features automatic bookkeeping, invoicing, tax calculations, way bill generation and remote printing. Additional interfaces for payment imports using FinTS and exports to Datev, Stotax, Lexware. Built with self-developed backend framework including custom ORM and user rights management with full separation of frontend SPA and backend.