The Runtime blog
How to give AI agents their own computers: builds, costs and security, with code that runs.
- How prompt injection becomes code execution, and how to contain itPrompt injection becomes code execution when an agent with a shell obeys text it read; you contain it by limiting what that shell can reach.
- How to give an AI agent its own computer: four ways comparedGive an AI agent a disposable machine of its own: your laptop, a Docker container, a virtual machine, or a cloud sandbox made for agents.
- Pause, don't delete: why agent sandboxes should sleep between turnsPause an agent's sandbox between turns: it keeps memory, processes and files, wakes in milliseconds, and pays only for storage.
- Run Claude Code overnight in the cloud and wake up to a pull requestStart Claude Code headless in a cloud sandbox, let it push a branch and open a draft pull request, then review it in the morning.
- What 1,000 AI agent runs cost, line by lineA thousand five-minute agent runs on 2 vCPU, 4 GiB sandboxes cost $3.54 on Runtime: CPU used plus memory held.