<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <id>https://mederic.me/blog</id>
  <title>Mederic Burlet · Blog</title>
  <updated>2026-06-29T00:00:00.000Z</updated>
  <link rel="alternate" href="https://mederic.me/blog"/>
  <link rel="self" href="https://mederic.me/blog/atom.xml"/>
  <author>
    <name>Mederic Burlet</name>
    <uri>https://mederic.me</uri>
  </author>
  <generator version="0.1.0">Neurowire</generator>
  <entry>
    <id>https://mederic.me/blog/neurowire-taps-pack</id>
    <title>Neurowire Taps Pack: 271 curated sources, 24 themes</title>
    <link rel="alternate" href="https://mederic.me/blog/neurowire-taps-pack"/>
    <updated>2026-06-29T00:00:00.000Z</updated>
    <published>2026-06-29T00:00:00.000Z</published>
    <author>
      <name>Mederic Burlet</name>
      <uri>https://mederic.me</uri>
    </author>
    <category term="open-source"/>
    <category term="feeds"/>
    <summary type="text">The Taps Pack is a ready-made library of 271 vetted sources for Neurowire, grouped into 24 themes from Frontier AI Labs to Food. It's the curation layer ahead of the upcoming Neurowire SaaS.</summary>
  </entry>
  <entry>
    <id>https://mederic.me/blog/neurowire-docs-launch</id>
    <title>Neurowire: an open feed engine, now with full docs</title>
    <link rel="alternate" href="https://mederic.me/blog/neurowire-docs-launch"/>
    <updated>2026-06-28T00:00:00.000Z</updated>
    <published>2026-06-28T00:00:00.000Z</published>
    <author>
      <name>Mederic Burlet</name>
      <uri>https://mederic.me</uri>
    </author>
    <category term="open-source"/>
    <category term="feeds"/>
    <summary type="text">Neurowire turns any source, even feed-less websites, into one canonical feed you can serialize to Atom, JSON Feed, Markdown, RSS, or its own compact NWF format. The full documentation site is now live.</summary>
  </entry>
  <entry>
    <id>https://mederic.me/blog/why-ai-pilots-stall</id>
    <title>Why AI pilots stall before production</title>
    <link rel="alternate" href="https://mederic.me/blog/why-ai-pilots-stall"/>
    <updated>2026-06-25T00:00:00.000Z</updated>
    <published>2026-06-20T00:00:00.000Z</published>
    <author>
      <name>Mederic Burlet</name>
      <uri>https://mederic.me</uri>
    </author>
    <category term="ai-adoption"/>
    <category term="enablement"/>
    <summary type="text">AI pilots stall because they optimise for a demo, not for adoption. Production requires architecture, guardrails, and a change in how teams work, not a better model.</summary>
  </entry>
  <entry>
    <id>https://mederic.me/blog/mcp-systems-for-real-teams</id>
    <title>Designing MCP systems for real teams</title>
    <link rel="alternate" href="https://mederic.me/blog/mcp-systems-for-real-teams"/>
    <updated>2026-05-30T00:00:00.000Z</updated>
    <published>2026-05-30T00:00:00.000Z</published>
    <author>
      <name>Mederic Burlet</name>
      <uri>https://mederic.me</uri>
    </author>
    <category term="mcp"/>
    <category term="agents"/>
    <summary type="text">Good MCP systems expose a few high-leverage tools with clear boundaries, not every API you have. Scope, access control, and observability matter more than autonomy.</summary>
  </entry>
  <entry>
    <id>https://mederic.me/blog/700-engineers-on-adoption</id>
    <title>What 700 trained engineers taught me about adoption</title>
    <link rel="alternate" href="https://mederic.me/blog/700-engineers-on-adoption"/>
    <updated>2026-05-12T00:00:00.000Z</updated>
    <published>2026-05-12T00:00:00.000Z</published>
    <author>
      <name>Mederic Burlet</name>
      <uri>https://mederic.me</uri>
    </author>
    <category term="enablement"/>
    <category term="ai-adoption"/>
    <summary type="text">After training 700+ practitioners, the pattern is clear: adoption is a behaviour change, not a tooling rollout. Role-specific practice and internal champions are what make it stick.</summary>
  </entry>
</feed>
