<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Tascarrel Blog</title><description>Engineering articles about isolated development environments, coding agents, and Tascarrel.</description><link>https://tascarrel.dev/</link><item><title>Tascarrel&apos;s Isolation Model</title><link>https://tascarrel.dev/blog/how-tascarrel-isolates-coding-agents/</link><guid isPermaLink="true">https://tascarrel.dev/blog/how-tascarrel-isolates-coding-agents/</guid><description>Tascarrel combines a VM boundary around the complete development environment
with container-based pods for disposable tasks. This article explains how
layered isolation, reusable environment definitions, network controls,
credential mediation, and Git publication form one coherent isolation model,
along with its trust assumptions and limits.
</description><pubDate>Sun, 26 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Isolating Coding Agents</title><link>https://tascarrel.dev/blog/isolating-coding-agents/</link><guid isPermaLink="true">https://tascarrel.dev/blog/isolating-coding-agents/</guid><description>Safely running a coding agent requires isolating both the agent and all
development code it executes, including dependencies, build scripts, tests,
and project tools. This article explains why command approvals are not an
isolation boundary, compares operating-system sandboxes, containers,
user-space kernels, virtual machines, and dedicated machines, and examines
the network, credential, publication, state, environment, and hosting
decisions needed to make isolation effective in practice.
</description><pubDate>Sat, 25 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>