Hi, I'm Luisa.
I'm an independent advisor working on agentic AI systems and how to make them secure by design. I build tools at liwala.dev , and write about the architectural decisions behind my work here and on my Substack, Herding Agents .
Recent essays
-
How I set out to build a coding agent orchestrator and ended up writing a config auditor instead
Building (almost) in public, coding agents, security, and breaking from platform lock-in
-
The most useful AI agents are dangerous by design
The capabilities that make agents useful are the same ones that make them exploitable
-
We are all herding agents...
Thoughts on doing it right
Recent notes
-
Slower loops, stronger signal
Quick feedback loops are necessary (but not sufficient) scaffolding for AI-assisted coding.
-
Build the scaffolding, not the system
As software engineers, our job is to decompose a system into pieces, then to build out those pieces.