Agentic infrastructure
The question: What infrastructure do AI agents need to run long, stateful work against private systems, safely and cheaply?
Agents that debug real systems need a place to run: a shell, tools, files, and network access to private APIs, for hours at a time. This journey is about that place.
What we think now
Revision 1, 2026-03-21.
- Sandboxes must run inside our own network. Hosted sandboxes offer that only on enterprise plans, from about $3K a month.
- Persistence comes first. A sandbox has to survive timeouts and node loss; one 11-hour session survived a spot instance termination.
- Design for idle time. Per 20 GB, a running sandbox costs about $5 a month, a paused one about $1.60 (resumes in about 5 seconds), an archived one about $0.50 (about 30 seconds). At 200 sandboxes with 80% idle, that is about $200 a month instead of $1,000.
- Build on Kubernetes (OpenSandbox on EKS), with a network policy per sandbox and agents running unprivileged.
Open questions
- Is container isolation enough, or do we need gVisor, Kata or Firecracker?
- Can the same sandbox run on a laptop?
- Can archiving and pre-warming be driven by usage numbers instead of fixed timers?
Entries
- We Tried Every AI Sandbox. Then We Built Our Own. 2026-03-21, start, 12 min, 4.0k tokens
Follow this journey: RSS. Plain text version: /journeys/agentic-infrastructure.md