<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Workflow - Tag - Shengxu · Cloud Architecture &amp; DevOps</title><link>https://shengxu.pages.dev/en/tags/workflow/</link><description>Cloud architecture &amp; DevOps notes by Shengxu: Kubernetes, Cilium, observability, LLM infra, AI agents.</description><generator>Hugo 0.153.2 &amp; FixIt v0.4.0-alpha.3-20251225101113-8ffb9a95</generator><language>en</language><lastBuildDate>Sat, 09 May 2026 16:28:25 +0800</lastBuildDate><atom:link href="https://shengxu.pages.dev/en/tags/workflow/index.xml" rel="self" type="application/rss+xml"/><item><title>Two Real Problems in AI Programming: Multi-Project Task Management and Multi-User Collaboration Isolation</title><link>https://shengxu.pages.dev/en/posts/ai-agent-multi-project-collaboration-isolation/</link><pubDate>Sat, 09 May 2026 16:28:25 +0800</pubDate><guid>https://shengxu.pages.dev/en/posts/ai-agent-multi-project-collaboration-isolation/</guid><category domain="https://shengxu.pages.dev/en/categories/ai/">AI</category><description>&lt;p&gt;In multi-project, multi-developer AI programming practice, the continuity of task status and the isolation of personal configurations are key pain points affecting efficiency. This article proposes an engineering solution based on &amp;ldquo;sub-project Source of Truth&amp;rdquo; and &amp;ldquo;local rule isolation,&amp;rdquo; aiming to address cross-project task breakpoint management and team configuration pollution, while providing a replicable directory structure, read/write boundaries, and backup strategy.&lt;/p&gt;
&lt;hr&gt;
&lt;p&gt;Once an engineer starts using AI agents to write code frequently, the problem they quickly encounter isn&amp;rsquo;t &amp;ldquo;Can AI write functions?&amp;rdquo; but a more practical set of issues.&lt;/p&gt;</description></item></channel></rss>