Blog
Notes on building EU-sovereign browser infrastructure for AI agents.
-
Build vs buy: what a browser fleet actually costs
The compute bill is the small number. A model for the real cost of running your own browser infrastructure, and the three cases where building wins.
Read the post -
Data residency for AI agents: what reviews really ask
Region settings answer the easy question. The seven questions a European data protection review actually asks about agents, and why one is usually missed.
Read the post -
From RPA to agents: what changes when the bot reads
Agents do not replace RPA, they move where the decisions live. What that changes about cost, testing and governance, and what stays exactly the same.
Read the post -
Securing browser agents: injection, credentials, blast radius
A browser agent reads untrusted text and can act on it. Three controls that work, three that do not, and where the boundary genuinely belongs.
Read the post -
When there is no API: extracting from closed systems
Screen scraping never went away, it moved to the browser. A working method for pulling reliable data out of systems that will not export it.
Read the post -
Why browser agents fail in production
A taxonomy of the eight ways browser automation actually breaks, why four of them are silent, and what to measure so you find out before your users do.
Read the post