Running untrusted AI-generated code safely is the obvious hard problem.
But sometimes the problems that break an agent workflow look like boring infrastructure work.
v0.6 began as plumbing:
Persistent sandbox registry
Automatic cleanup with TTL
Running untrusted AI-generated code safely is the obvious hard problem. But sometimes the problems...
Running untrusted AI-generated code safely is the obvious hard problem.
But sometimes the problems that break an agent workflow look like boring infrastructure work.
v0.6 began as plumbing:
Persistent sandbox registry
Automatic cleanup with TTL

We built persistent memory. We built workflow orchestration. We never built the layer that keeps the...

You know that slightly cursed feeling when an AI coding agent says "done", but you still have no idea...

I’ve been thinking a lot about a failure mode in AI-assisted development that does not fit neatly...

This is Part 2 of Closing the execution gap — a series on building jhansi.io, a cloud sandbox for...

A few weeks ago I started building SafeRun — inline reliability infrastructure for AI agents in...

A few weeks ago I started building SafeRun — inline reliability infrastructure for AI agents in...