<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Luge Blog</title><description>Posts on AI agents, attributed team memory, humans in the loop, and AI that runs on your side. Written by the team building Luge.</description><link>https://luge.nsolutions.ai</link><language>en-CA</language><item><title>The Luge method</title><link>https://luge.nsolutions.ai/en/blog/the-luge-method</link><guid isPermaLink="true">https://luge.nsolutions.ai/en/blog/the-luge-method</guid><description>One developer, a fleet of agents: backlog triage, tickets, tech watch and the nightly board sweep all run through Luge itself. Read off the live instance.</description><pubDate>Mon, 24 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Delegate, don&apos;t operate</title><link>https://luge.nsolutions.ai/en/blog/delegate-dont-operate</link><guid isPermaLink="true">https://luge.nsolutions.ai/en/blog/delegate-dont-operate</guid><description>Driving an AI gesture by gesture is still doing the work yourself. Luge&apos;s founding principle: hand objectives to AI colleagues — with the four pillars that make delegation possible.</description><pubDate>Wed, 19 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Why we built an AI employee, not a chatbot</title><link>https://luge.nsolutions.ai/en/blog/why-an-ai-employee-not-a-chatbot</link><guid isPermaLink="true">https://luge.nsolutions.ai/en/blog/why-an-ai-employee-not-a-chatbot</guid><description>A chatbot answers and forgets. An employee learns, remembers who taught it what, and carries the work through. The manifesto behind Luge, in five ideas.</description><pubDate>Fri, 14 Aug 2026 00:00:00 GMT</pubDate></item></channel></rss>