From the engine room

Blog

Notes on AI agents, microVMs, secure code execution, and European cloud infrastructure.

06

Latest article

Person on a sofa with a coffee mug, reading a chat conversation on a laptop.
AI agents 8 min read

How to create your own Cowork agent in Microsoft Teams

Anthropic's Claude Cowork gave everyone a working mental model for chat-driven agents. Here is how to build that same shape yourself, inside a Teams chat, on infrastructure you control.

Read article
05

All articles

Server hardware representing the infrastructure behind sandbox microVMs.
Engineering

Why We Replaced SSH With a Custom Daemon Inside Our Sandbox VMs

A warm pool bug that SSH could not fix forced us to rethink how the host talks to a sandbox. Here is what we built, why it is faster, and why per-sandbox env vars finally work.

Read article
Server racks connected by bundles of network cables.
Security

How to Isolate AI Coding Agents: Comparing Every Major Approach

A factual comparison of Docker Sandboxes, E2B, Daytona, and ZWRM for isolating AI coding agents, including where they run, how they isolate, and what they let agents do.

Read article
Close-up of Europe on a printed globe.
Digital sovereignty

Why Digital Sovereignty Matters for European Companies

The CLOUD Act, Schrems II, and why the location of your cloud provider's headquarters matters more than the location of its data centers.

Read article
Close-up of source code on a computer screen.
AI agents

What AI Coding Agents Can Do When They Have Their Own Environment

AI agents are more than chatbots. When you give them a real environment to work in, they can build, deploy, and manage entire applications. Here's what that looks like.

Read article
Snow-covered mountains rising above a layer of clouds at sunset.
Security

Deploying AI Agents Safely with Hardware Isolation

AI agents execute arbitrary code. Here's how microVM sandboxing makes that safe for production.

Read article