# Blog

> Sandscale news, releases and how-tos, written plainly.

News, releases and how-tos from the Sandscale team.

- [November 20, 2026 · **Awake-time billing for agent sandboxes: what you pay for and what you don't** · How Sandscale bills agent sandboxes by awake vCPU-hours, with idle time free. Includes a worked example with the arithmetic shown.](https://sandscale.dev/blog/awake-time-billing-agent-sandboxes)
- [November 20, 2026 · **Running Claude Code, Codex and Gemini CLI under policy on Sandscale** · Two ways to run coding agents on Sandscale, what policy enforces for Claude Code versus what it only records for Codex and Gemini CLI, and the gaps.](https://sandscale.dev/blog/coding-agents-under-policy-sandscale)
- [November 20, 2026 · **Containers, gVisor or Firecracker: how to isolate code your AI agent wrote** · A plain comparison of containers, gVisor and Firecracker microVMs for running untrusted agent code: threat model, how each works, and what each costs.](https://sandscale.dev/blog/isolating-ai-agent-code-containers-gvisor-firecracker)
- [November 20, 2026 · **Keeping secrets out of agent prompts: how Vault and DLP fit together** · How a secret leaks from an AI agent run, what Sandscale Vault and DLP each cover, and the paths neither closes. Documented behavior only.](https://sandscale.dev/blog/secrets-out-of-agent-prompts-vault-dlp)

---
Source: https://sandscale.dev/blog
