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.
The front end built for the PROTOS miniHIL, a small hardware-in-the-loop test rig. It is a React (Next.js) app that lets you watch a test run on the hardware as it happens: live logs, signal traces and execution state, all streamed from the device while the test executes. The harder problem behind the views was the data path and performance. A test run produces a lot of data on an MCU. Additionally, the goal was to allow the user to open multiple browser windows showing different aspects of the test run.
The data comes off the miniHIL hardware itself, an STM32-based MCU system that runs the test cases in real time. The hardware is connected to the PC via USB (1.1 full speed device). A Java backend on the PC owns that USB link, deserializes the low-level protocols, and exposes the result to the GUI over a WebSocket. Inside the browser a single shared worker holds the websocket connection and fans the decoded stream out to every open window.
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.