Persistent execution increases usefulness while storage reuse raises the isolation bar.
Customers want state to survive useful work, while security reviewers need proof that one workload leaves nothing for the next.
Who you’d be doing this for
“Security asked me what happens to the disk after a task ends, and I had no proof to send.”
Majid Rizk · Frontend Platform Engineer
Owns deployment standards for a JavaScript team evaluating Persistent Sandboxes for AI-assisted internal applications.
What is at stake
Security reviewers are blocking Persistent Sandbox use until storage isolation is demonstrable. You must weigh a stronger customer guarantee against startup performance and regional consistency.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- persistent state vs clean isolation
- startup latency vs storage verification
- customer adoption vs bounded security claims
- regional consistency vs launch speed
Why Vercel
Persistent Sandboxes run alongside the compute infrastructure that hosts untrusted and agent-generated code.
Written with these in mind
Not your kind of problem? 22 more at Vercel, or browse every organization.
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.