~/blog
Blog
I write about what I pick up along the way: building product with AI, leading an engineering team and raising two German Shepherds. Remote, from El Salvador.
Articles
- I don't just review the agent's code anymore. I ask for proofSix Playwright flows that leave a screenshot, video and trace on failure. In CI on every PR and every deploy. And four times the evidence proved me wrong.
- I made a Nintendogs of my dog101 blended shapes, 10 layers of fur and one day with Claude. From the side it's Dante; from the front, not quite.
- Seven years remote: impostor syndrome didn't leave, but it's a lot smaller nowSeven years working remotely from El Salvador for US teams. Impostor syndrome didn't go away all at once, it just kept getting smaller.
- Nobody reviews their own code well, not even an agentThree bugs that passed tests and review without looking odd. A fresh reviewer, human or agent, won't see them without knowing something the author didn't.
- My subagents reminded me of Naruto's shadow clonesI built eight subagents across two repos. In 18 hours they ran 27 times, 11 as real agents: what I delegate, what they found and what I still don't know.
- My prompt couldn't add, and my eval didn't say whyI built an LLM scorer with a threshold I never measured and eyeballed it until something showed up. Two weeks later: 39 labels and a bug in the prompt.
- How this blog is builtNext.js with static export, MDX posts inside the repo and no external services. Why I picked the simplest option and what I left out on purpose.