Local Image Generation with Bonsai Image 4B
Notes from setting up Bonsai Image 4B locally on Apple Silicon, debugging the first failed path, wrapping the working pipeline in a reusable CLI, and using it from any project directory.
Read moreSoftware quality, engineering, automation, AI
Practical writing on software quality, test automation, engineering leadership, and the evolving role of AI in delivery workflows. I also run private workshops for QA and engineering teams in English and Polish.
Hi! I'm Sławomir Radzymiński, a passionate test engineer and AI enthusiast based in the beautiful city of Kraków.
I'm a seasoned test engineer specializing in software quality and test automation, with extensive experience integrating these practices into CI/CD processes. I'm particularly passionate about the practical application of artificial intelligence in testing and software engineering – from generating test plans and test cases, through creating automated tests, to intelligent risk analysis. As a Senior Staff Test Engineer at Ocado Technology, I focus on modern techniques for delivering high-quality products in the shortest possible time, sharing my knowledge and expertise both at work and as a trainer with various companies and universities.
Beyond the world of testing and AI, I cherish my time with my wonderful family and stay active with squash, scrabble challenges, and exploring new destinations. I maintain my fitness with regular gym sessions and love unwinding with TV series alongside my wife – always striving to balance my passion for technology with the joys of everyday life.
Notes from setting up Bonsai Image 4B locally on Apple Silicon, debugging the first failed path, wrapping the working pipeline in a reusable CLI, and using it from any project directory.
Read moreHow a local testing stack evolved from one Docker-based environment into three distinct runtime profiles with clearer intent: lightweight, full, and server.
Read moreA practical mental model for developers: understand LLMs, AI agents, function calling, and why coding agents built on the same model behave differently.
Read more