<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Local LLM Practice Notes</title><link>https://k-moonshot.kr/en/</link><description>From local inference to retrieval, access controls and operations: ask better questions before an institutional AI deployment.</description><language>en</language><item><title>Design the document pipeline before choosing a local LLM</title><link>https://k-moonshot.kr/en/briefs/local-llm-document-pipeline/</link><guid isPermaLink="true">https://k-moonshot.kr/en/briefs/local-llm-document-pipeline/</guid><description>Map the internal path from document extraction to source-grounded answers.</description><pubDate>Wed, 04 Nov 2026 15:00:00 GMT</pubDate></item><item><title>Security boundaries still matter for on-premise AI</title><link>https://k-moonshot.kr/en/briefs/onprem-security-boundaries/</link><guid isPermaLink="true">https://k-moonshot.kr/en/briefs/onprem-security-boundaries/</guid><description>Model location and operational data control need to be assessed together.</description><pubDate>Wed, 04 Nov 2026 15:00:00 GMT</pubDate></item></channel></rss>