Blog
Wallapop: The Invisible Engineering Behind Europe's Largest Circular Marketplace
Upload a photo of a bicycle to Wallapop. In under 200 milliseconds, a cascade of real-time Machine Learning models classifies the item, …
Halt and Catch Fire: The Cult TV Series That Understood Software Engineering Better Than Silicon Valley
Almost every Hollywood production about technology makes the same unforgivable mistake: reducing computing to neon-green terminal screens …
MLOps for Engineers: How to Take an AI Model from Jupyter to Production Without Dying in the Attempt
Building a Machine Learning model in a Jupyter notebook is easy; keeping it alive, accurate, and monitored in production with real-world …
Ada Lovelace: The Countess Who Programmed the Future 100 Years Before Computers Existed
In 1843, an English countess and daughter of Lord Byron wrote the first computer program for a mechanical engine that was never built. She …
Prompt Injection: The Vulnerability Your AI Agent Doesn't Know It Has
Your CrewAI agent has the same problem web servers had in 2005: it accepts user input without sanitizing. Prompt Injection is the #1 …
Fine-Tuning vs Prompt Engineering vs RAG: When to Use Each (And the Fourth Option Nobody Mentions)
Your AI model hallucinates with your company’s data. Is the fix RAG, fine-tuning, or a better prompt? The right answer depends on a single …
An Engineer's Productivity Stack in 2026: The Tools I Use Every Day
After 60+ articles, 9 technical series, and 4 production applications, this is the real stack I use every day. No sponsorships, no …
Flywire: How a Spaniard Built the Brain of International Payments from Boston
When a Korean student tries to pay tuition at a university in Madrid, they face a maze of opaque banking fees, unfavorable exchange rates, …
Thomas Bayes: The Reverend Who Taught Us to Update Our Beliefs with Data
How do you update your opinion when you receive new evidence? If your answer is ‘with data,’ congratulations: you’ve been practicing …
RAG in Production: 7 Anti-Patterns That Destroy Precision (And How I Fixed Them)
RAG is the aspirin of generative AI: everyone prescribes it, almost no one truly understands how it works, and when it fails, the patient …