<?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 knowledged.to</title><link>https://knowledged.to/tags/architecture/</link><description>Recent content in Architecture on knowledged.to</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 25 May 2026 22:47:08 +0530</lastBuildDate><atom:link href="https://knowledged.to/tags/architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>Sub-Agent vs Tool-Agent in AI Harness Engineering</title><link>https://knowledged.to/notes/ml/sub-agent-vs-tool-agent/</link><pubDate>Mon, 25 May 2026 17:16:33 +0000</pubDate><guid>https://knowledged.to/notes/ml/sub-agent-vs-tool-agent/</guid><description>Distinguishes sub-agents from tool-agents by autonomy, interface, context, and harness contract.</description></item><item><title>MCP Interaction Model</title><link>https://knowledged.to/notes/ml/mcp-interaction-model/</link><pubDate>Sat, 16 May 2026 17:21:30 +0000</pubDate><guid>https://knowledged.to/notes/ml/mcp-interaction-model/</guid><description>Deep-dive into the Model Context Protocol interaction model covering components, OAuth 2.1 authorization, initialization, capability discovery, tool calling, sampling, and elicitation.</description></item><item><title>Defense-in-Depth</title><link>https://knowledged.to/notes/security/defense-in-depth/</link><pubDate>Fri, 01 May 2026 16:17:32 +0000</pubDate><guid>https://knowledged.to/notes/security/defense-in-depth/</guid><description>Overview of the defense-in-depth security strategy, its layered controls, core assumptions, and applications beyond IT</description></item><item><title>Mixture of Experts (MoE)</title><link>https://knowledged.to/notes/ml/mixture-of-experts/</link><pubDate>Thu, 23 Apr 2026 16:04:47 +0000</pubDate><guid>https://knowledged.to/notes/ml/mixture-of-experts/</guid><description>Overview of MoE architecture, routing, key components, variants, and trade-offs in machine learning models</description></item></channel></rss>