Blog
Notas breves sobre cómo sacar adelante proyectos con AI driven development: el proceso, el alcance y lo que de verdad funciona.
La web que Google no veía
Search Console decía 23 páginas. La web tenía 86. Entre las que faltaban estaban la portada, los servicios y la página de contacto, y nada en la web parecía estar mal.
Leer el artículo →Más artículos en inglés
No todo está traducido todavía. Estos solo están en inglés:
One laptop, $6.3 billion: what the Binance hack teaches small teams
Binance says the biggest crypto theft on record started with an engineer's compromised laptop. You are not an exchange, but the lessons about access, limits and alarms scale all the way down.
Leer →Claude Duet and the agent that asks first
Anthropic's new proactive agent works in the background and waits for a yes before it sends, pays, signs or deletes anything. That design choice is the real news, and it is a good rule for any agent you let near your business.
Leer →The bugs are not in the code
A shop had been live for months and could not take a single order. The code was fine: all three failures lived outside the repository.
Leer →Going live is the hard part
AI writes the first 90% fast. The last 10% — payments that fail, forms that swallow leads, backups nobody has restored — is where projects quietly die.
Leer →Finishing is a separate skill
AI made starting free. It did not make finishing any easier — so people start more and finish less. What actually raises the odds a project reaches real users.
Leer →