<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
      <title>Alek&#x27;s Blog - agents</title>
      <link>https://blog.none.at</link>
      <description>Production notes on Kubernetes, OpenShift, and OVHcloud: observability, log archiving, service mesh, LLM inference, and digital sovereignty.</description>
      <generator>Zola</generator>
      <language>en</language>
      <atom:link href="https://blog.none.at/tags/agents/rss.xml" rel="self" type="application/rss+xml"/>
      <lastBuildDate>Thu, 09 Jul 2026 00:00:00 +0000</lastBuildDate>
      <item>
          <title>Who Has Access? Humans, Accounts, AI Agents</title>
          <pubDate>Thu, 09 Jul 2026 00:00:00 +0000</pubDate>
          <author>aleks</author>
          <link>https://blog.none.at/blog/2026/2026-07-09-sovereignty-access-model/</link>
          <guid>https://blog.none.at/blog/2026/2026-07-09-sovereignty-access-model/</guid>
          <description xml:base="https://blog.none.at/blog/2026/2026-07-09-sovereignty-access-model/">&lt;p&gt;&lt;a href=&quot;https:&#x2F;&#x2F;blog.none.at&#x2F;blog&#x2F;2026&#x2F;2026-07-09-sovereign-cloud-washing&#x2F;&quot;&gt;Part 1&lt;&#x2F;a&gt; split the technology-supply-chain
question into two halves: what the platform is built on, and who — or what — actually has access to
it. &lt;a href=&quot;https:&#x2F;&#x2F;blog.none.at&#x2F;blog&#x2F;2026&#x2F;2026-07-09-sovereignty-technology-stack&#x2F;&quot;&gt;Part 2&lt;&#x2F;a&gt; answered the first half. This
post answers the second, using systems already built and operated for this blog rather than new
research — human access, service-account access, and (increasingly relevant) AI-agent access, all
checked against the same bar: is it documented, is it audited, and is it technically enforced or
just expected to be followed.&lt;&#x2F;p&gt;</description>
      </item>
      <item>
          <title>LLM Inference on OVH MKS: Connect IDEs and Web UIs</title>
          <pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate>
          <author>aleks</author>
          <link>https://blog.none.at/blog/2026/2026-06-02-llm-inference-on-ovh-agents/</link>
          <guid>https://blog.none.at/blog/2026/2026-06-02-llm-inference-on-ovh-agents/</guid>
          <description xml:base="https://blog.none.at/blog/2026/2026-06-02-llm-inference-on-ovh-agents/">&lt;p&gt;The first four parts of this series deployed a vLLM inference endpoint at
&lt;code&gt;https:&#x2F;&#x2F;llm.YOUR_DOMAIN&#x2F;v1&lt;&#x2F;code&gt;, protected by a Bearer token, running on an OVH RTX5000-28 GPU node.
This part shows how to connect coding assistants, web UIs, and other OpenAI-compatible clients
to that endpoint.&lt;&#x2F;p&gt;</description>
      </item>
    </channel>
</rss>
