<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Architecture on Xinwei Xiong (cubxxw) - AI, Open Source &amp; Nomad Blog</title>
    <link>https://nsddd.top/tags/architecture/</link>
    <description>Recent content in Architecture on Xinwei Xiong (cubxxw) - AI, Open Source &amp; Nomad Blog</description>
    <image>
      <title>Xinwei Xiong (cubxxw) - AI, Open Source &amp; Nomad Blog</title>
      <url>https://nsddd.top/assets/og-image.png</url>
      <link>https://nsddd.top/assets/og-image.png</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 24 Jun 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://nsddd.top/tags/architecture/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building a Production-Grade AI Agent System from Scratch: A Full Architecture Breakdown of Relay</title>
      <link>https://nsddd.top/ai-technology/posts/relay-agent-architecture-design/</link>
      <pubDate>Wed, 24 Jun 2026 10:00:00 +0800</pubDate>
      
      <guid>https://nsddd.top/ai-technology/posts/relay-agent-architecture-design/</guid>
      <description>Using the Relay open-source job-search Agent project as a case study, this article fully breaks down every key design decision in a production-grade multi-agent system: why split a single Agent into 5, how to implement HITL checkpoints with LangGraph, how a three-tier LLM router precisely tracks costs, how a fabrication guard validates at runtime, and how a hybrid backend (Hono/Bun &#43; FastAPI/Python) decouples cleanly. Whether you are building your first Agent PoC or pushing toward production, there are design patterns here you can take away.
</description>
    </item>
    
    <item>
      <title>The Agent Engineering Map: Where Does That 98.4% of the Work Actually Live?</title>
      <link>https://nsddd.top/ai-technology/posts/agent-engineering-the-98-percent-harness/</link>
      <pubDate>Wed, 17 Jun 2026 09:30:00 +0800</pubDate>
      
      <guid>https://nsddd.top/ai-technology/posts/agent-engineering-the-98-percent-harness/</guid>
      <description>A panoramic map that treats Agent Engineering as a discipline. Starting from the widely cited claim that only 1.6% of Claude Code is AI decision logic while 98.4% is infrastructure, it walks the eight pillars one by one — orchestration, context, memory, tools, reliability, evaluation, cost, governance — explaining the gap each fills, its minimal implementation, and its failure boundary. It fuses 2025 to 2026 frontline engineering from Anthropic, OpenAI, Cognition, Manus, and Temporal, and lands on one line: the model is bought, the harness is built, and your entire engineering leverage lives in that 98.4%.
</description>
    </item>
    
  </channel>
</rss>
