Builds
Built an automation that scans my entire Gmail for a full calendar year, finds everything that looks like a receipt or business expense, and organizes it all into Google Drive. Tax season went from painful to painless.
An AI agent that knows my food preferences, knows where I am, and does the full work — personalized recommendations, OpenTable links to book, Google Maps directions. It learns what I like over time.
More builds coming soon. Currently breaking things so you don't have to.
About
That's the moment I got hooked.
I'm Rodrigo, a Lead Software Engineer. I've spent years building software at scale, shipping products, dealing with the messy parts of real systems. Now I spend my nights and weekends wiring up AI into workflows and seeing what actually holds up when you throw real data at it.
Some of it didn't break. Some of it isn't there yet. I share both here.
My theory
Because AI is so accessible now, everyone wants to make everything agentic. Throw an LLM at it, write some instructions in a markdown file, and hope it follows them. But LLMs are probabilistic — there's no enforcement. Hope is not a strategy.
The reality is that the best AI workflows live in the middle. Every good flow has a deterministic part and an agentic part. The deterministic part gives you reliability — hardcoded logic, structured data, predictable outcomes. The agentic part gives you flexibility — understanding context, handling ambiguity, making judgment calls.
Not everything needs to be an agent. Most people just need someone to look at their workflow, figure out which parts should be rock-solid code and which parts benefit from AI, and wire it up properly. That's what I do.
Stay in the loop
New builds, breakdowns, and the occasional thing that actually broke.
No spam. Just new posts.
Or find me here