From the interface you see to the systems behind it. Here’s where I spend my time building.
Connecting models to the tools and workflows that make them useful. I build the infrastructure between assistants, browsers, and the work people need to get done.
Sessions, logs, tokens, and the details that explain what a system is doing. I build developer tools that make complex work easier to inspect and improve.
Web applications, APIs, and the systems behind them. I like taking an idea through the whole process: build it, use it, learn from it, and keep making it better.
As Head of AI at TechInSF, I help teams put AI into practice. My work spans workflow automation, hands-on implementation, and helping people understand the tools they use.
Tools I’m building, problems I’m exploring, and the code behind them.
A native macOS gateway between AI assistants and browser agents. Less context overhead. More deliberate automation.
A local observer for coding agents. Bring sessions, token use, and API-price estimates into one place.
An open-source Instagram widget platform. A way to bring social content into a website you control.
I’m Angelo, a software and applied AI engineer based in San Francisco. I work across the whole system, and I like staying close to the people using it.
More about meMy projects often start with something I need in my own workflow. Using the tools is part of building them.
Clear interfaces, useful observability, and deliberate boundaries between components.
Public repositories, engineering notes, and lessons from what I’m building along the way.
The idea behind BrowserHelm, and separating navigation from the decisions that matter.
Read the note Project noteThe questions behind Agent Watchtower: activity, tokens, and what the numbers actually mean.
Read the note