A long conversation nearly made my posts depend on the redesign. The problem was leaving a critical decision too dependent on transient context.
Technology / career / artificial intelligence
Mentor dos Nerds
Felipe Abreu writes about applied AI, agents, automation, software architecture, and the human effects of increasingly capable systems.
Editorial archive
Recent reads
I was born in 1986 and survived at least nine ends of the world
After Y2K, 2012, and other waves of doomsday predictions, how to take AI transformation seriously without trading method for panic or euphoria.
The evolution of technology: from mainframes to real-time bad puns
How we went from rooms full of mainframes to agents that track context, execute tasks, and—with some judgment—know when to break the ice.
The Seductive Predictability of AI
How to use AI to expand agency without turning validation, availability, and personalization into an escape from the friction of human relationships.
AI in daily life isn't enough: I built an operation
How agents, memory, skills, and validations transform AI in daily life into a governed, reusable, and adaptable operation for businesses.
AI is not one thing: model, agent, automation, and harness
A guide to distinguishing model, agent, automation, and harness — and understanding where context, human control, and governance actually enter.