<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://loqy.work/blog/</id>
  <title>loqy blog</title>
  <link rel="self" href="https://loqy.work/atom.xml"/>
  <link rel="alternate" href="https://loqy.work/blog/"/>
  <updated>2026-08-12T00:00:00Z</updated>
  <author><name>Etienne</name></author>
  <entry>
    <id>https://loqy.work/blog/why-loqy-starts-local/</id>
    <title>Why loqy starts local and private by default</title>
    <link href="https://loqy.work/blog/why-loqy-starts-local/"/>
    <published>2026-08-12T00:00:00Z</published>
    <updated>2026-08-12T00:00:00Z</updated>
    <author><name>Etienne</name></author>
    <summary>Local-first is not a slogan for loqy. It is the product boundary that keeps work useful, inspectable, and under the user’s control.</summary>
  </entry>
  <entry>
    <id>https://loqy.work/blog/how-loqy-evaluates-local-models/</id>
    <title>How loqy evaluates local AI models for real work</title>
    <link href="https://loqy.work/blog/how-loqy-evaluates-local-models/"/>
    <published>2026-08-12T00:00:00Z</published>
    <updated>2026-08-12T00:00:00Z</updated>
    <author><name>Etienne</name></author>
    <summary>A useful local model is more than a benchmark score. loqy evaluates models against work, hardware, language, tools, and evidence.</summary>
  </entry>
  <entry>
    <id>https://loqy.work/blog/why-an-ai-agent-should-keep-evidence/</id>
    <title>Why an AI agent should keep the evidence in view</title>
    <link href="https://loqy.work/blog/why-an-ai-agent-should-keep-evidence/"/>
    <published>2026-08-12T00:00:00Z</published>
    <updated>2026-08-12T00:00:00Z</updated>
    <author><name>Etienne</name></author>
    <summary>An AI agent becomes trustworthy when its sources, actions, decisions, and deliverables remain attached to the work.</summary>
  </entry>
</feed>
