How to build a secure AI agent sandbox with relaxAI and Claude Code

Civo

Jun 18, 2026

AI agents are powerful. They're also unpredictable, non-deterministic, and capable of doing things you didn't ask them to do, as the Rome Alibaba and Claude Mythos case studies make very clear.

The answer isn't to avoid agentic AI. It's to run it properly.

In this demo, Ben Norris, founding engineer at relaxAI, shows how to build a fully sandboxed AI agent environment from scratch, an ephemeral Civo VM provisioned via Terraform and GitHub Actions, locked down with egress policies, an unprivileged Linux user, and hard resource caps, running a Claude Code session pointed at the relaxAI API.

The use case: an autonomous PR review agent that lists open pull requests, reviews the code, and posts comments directly into GitHub, all without touching your host infrastructure or exposing your credentials.

Watch the full webinar here —► https://www.civo.com/webinars/secure-execution-agents-in-sandboxes-with-relaxai

#relaxAI #Civo #AIAgents #SandboxedAI #ClaudeCode #SovereignAI #Terraform #GitHubActions #AgenticAI #PlatformEngineering #DevOps #CloudNative

====================
A new era of cloud computing, where speed, simplicity and predictable billing unite. Civo makes complexity a thing of the past.
Sign up to Civo -► https://www.civo.com

Subscribe to our YouTube Channel -► http://civo.io/subscribe

Follow Civo: