Notes on AI-assisted development, workflow patterns, and what I'm learning along the way. https://henriquesantana.work/blog/ 2026-06-03T08:00:00Z Henrique Santana https://henriquesantana.work/ https://henriquesantana.work/blog/agents-need-guardrails.html 2026-06-03T08:00:00Z 2026-06-03T08:00:00Z

People are wiring AI agents into production with permissions no human would get on day one. The fix isn't clever prompting. It's the same boring guardrails we use for new hires.

https://henriquesantana.work/blog/one-agent-per-dimension.html 2026-05-27T08:00:00Z 2026-05-27T08:00:00Z

I stopped asking one AI to review everything at once. Six focused agents, each checking a single dimension, produce sharper feedback in a third of the time.

https://henriquesantana.work/blog/ai-catches-its-own-lies.html 2026-05-20T08:00:00Z 2026-05-20T08:00:00Z

The same model that fabricates a claim will flag it as wrong five minutes later in a fresh session. I use that asymmetry as my primary workflow now.

https://henriquesantana.work/blog/linkedin-profile-score.html 2026-05-13T08:00:00Z 2026-05-13T08:00:00Z

I turned a recruiter's profile optimization guide into a scoring tool that reads your LinkedIn data export and tells you exactly what to fix.

https://henriquesantana.work/blog/skills-not-prompts.html 2026-05-12T08:00:00Z 2026-05-12T08:00:00Z

I stopped writing long prompts months ago. Everything I do with AI is skill-based now, and the difference in consistency and speed is enormous.

https://henriquesantana.work/blog/seo-for-ai-agents.html 2026-05-12T08:00:00Z 2026-05-12T08:00:00Z

Your website has two types of visitors now: humans and AI agents. Most sites are only optimized for one of them.