top of page


Beyond AUROC: Evaluating Visual Anomaly Detection for Real-World Production
High benchmark performance does not guarantee a reliable inspection system. This article presents a production-oriented framework for evaluating visual anomaly detection across thresholds, distribution shift, error costs, latency, validation, and monitoring.
15 hours ago3 min read


How I Completed Udacity's Agentic AI Nanodegree in 6 Hours
Udacity's Time on Sunday ☕️🥨 It was a Sunday morning in Munich. I had a cup of double espresso in hand, my laptop open, and a simple question in my head: how fast can I actually finish this? Six hours later, I had my answer — and a Udacity Nanodegree certificate to prove it. The Backstory I'll be honest. I didn't set out to break any records. I'm the CTO and Co-founder of 36ZERO Vision, a Munich-based company that builds AI-powered quality inspection systems for manufacturer
Feb 14 min read


ISO 27001 as a Growth-Stage Startup: Why I'd Do It Again (But Not Earlier)
ISO 27001 Experience You're scaling, enterprise clients are asking for security questionnaires, your team doubled, someone's laptop got stolen, and you realize your "security policy" is a Google Doc from 2022 nobody reads. Sound familiar? The Right Time to Do It Don't do it pre-PMF. Do it when: You have paying enterprise customers who actually ask for it Your team is 15-30+ people and processes are breaking You're handling sensitive data (manufacturing defects, customer IP, e
Jan 162 min read


Essential Python Packages for Early-Stage Startups: A CTO’s Perspective
Startup Python Bundle In the dynamic environment of an early-stage startup, the Chief Technology Officer (CTO) must make strategic decisions to ensure rapid development, scalability, and customer satisfaction. Python, renowned for its simplicity and extensive ecosystem, is an ideal programming language for startups aiming to deliver agile, customer-focused products. This article presents a curated selection of Python packages that facilitate professional project development,
May 18, 20255 min read


Proxy Tasks: Supercharging Image Understanding with Unlabelled Data
In the world of image-based computer vision, labeled data is the gold standard. However, the reality is that most image datasets are vast and unlabeled. This is where the clever use of proxy tasks shines, providing a strategic method to train your AI models effectively before honing them on smaller, labeled sets. Let's delve into how proxy tasks operate and why they are a game-changer for tackling image understanding challenges. The Unsupervised Learning Puzzle Unsupervised l
Jul 7, 20243 min read
bottom of page