<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>Manwe insights</title>
    <link>https://askmanwe.com/insights</link>
    <description>Essays, guides and research on ontology, AI sovereignty and how Manwe works.</description>
    <language>en</language>
    <item>
      <title>What it means for an agent to stay</title>
      <link>https://askmanwe.com/insights/what-it-means-for-an-agent-to-stay</link>
      <guid>https://askmanwe.com/insights/what-it-means-for-an-agent-to-stay</guid>
      <pubDate>Sat, 31 Oct 2026 09:00:00 GMT</pubDate>
      <description>Most AI "agents" are a prompt that disappears when the chat closes. A persistent advisor keeps its role, its lessons and its watches, and comes back when something changes.</description>
      <category>Product</category>
    </item>
    <item>
      <title>Your AI doesn't need a longer memory. It needs an ontology.</title>
      <link>https://askmanwe.com/insights/ai-needs-an-ontology</link>
      <guid>https://askmanwe.com/insights/ai-needs-an-ontology</guid>
      <pubDate>Fri, 30 Oct 2026 09:00:00 GMT</pubDate>
      <description>Chat history is a transcript, not an understanding. What makes context useful is knowing what things are, how they relate and why they matter.</description>
      <category>Ontology</category>
    </item>
    <item>
      <title>Worlds and Moons: context for a life with many projects</title>
      <link>https://askmanwe.com/insights/worlds-and-moons</link>
      <guid>https://askmanwe.com/insights/worlds-and-moons</guid>
      <pubDate>Wed, 28 Oct 2026 09:00:00 GMT</pubDate>
      <description>Your company, your studies and your home renovation shouldn't share one memory. A practical guide to giving each part of your life its own context, and knowing when to split it further.</description>
      <category>Ontology</category><category>Product</category>
    </item>
    <item>
      <title>Three models, one question: why disagreement is the useful part</title>
      <link>https://askmanwe.com/insights/why-disagreement-is-useful</link>
      <guid>https://askmanwe.com/insights/why-disagreement-is-useful</guid>
      <pubDate>Tue, 27 Oct 2026 09:00:00 GMT</pubDate>
      <description>A single confident answer hides its weak points. Putting the same question to several models shows you where the reasoning is solid and where it's a guess.</description>
      <category>Research</category><category>Product</category>
    </item>
    <item>
      <title>AI sovereignty starts on the computer you own</title>
      <link>https://askmanwe.com/insights/ai-sovereignty-starts-on-your-computer</link>
      <guid>https://askmanwe.com/insights/ai-sovereignty-starts-on-your-computer</guid>
      <pubDate>Sat, 24 Oct 2026 09:00:00 GMT</pubDate>
      <description>Sovereignty isn't a slogan about where data centres are. For a person or a small team, it comes down to three practical questions about your context, your models and your exits.</description>
      <category>Sovereignty</category>
    </item>
    <item>
      <title>How to hand an AI your research materials</title>
      <link>https://askmanwe.com/insights/how-to-hand-an-ai-research-materials</link>
      <guid>https://askmanwe.com/insights/how-to-hand-an-ai-research-materials</guid>
      <pubDate>Tue, 20 Oct 2026 09:00:00 GMT</pubDate>
      <description>The quality of AI research depends less on the model than on what you give it and what you ask for. A practical guide to briefs, sources, folders and checking the result.</description>
      <category>Research</category>
    </item>
  </channel>
</rss>