<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>PKM on Thede Technologies</title><link>https://thedetech.com/tags/pkm/</link><description>Recent content in PKM on Thede Technologies</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 16 Oct 2026 19:52:17 -0500</lastBuildDate><atom:link href="https://thedetech.com/tags/pkm/index.xml" rel="self" type="application/rss+xml"/><item><title>The architecture of advice</title><link>https://thedetech.com/blog/2026-05-11-architecture-of-advice/</link><pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate><guid>https://thedetech.com/blog/2026-05-11-architecture-of-advice/</guid><description>&lt;p>In &lt;a href="https://thedetech.com/blog/2026-05-07-30-days-of-ai-collaboration/">the last post&lt;/a> I looked at the sheer &lt;em>volume&lt;/em> of AI-assisted engineering: 55,000 turns of professional capital recovered from a single month. But once you have the data, you stop asking &amp;ldquo;how much?&amp;rdquo; and start asking &amp;ldquo;what kind?&amp;rdquo;&lt;/p>
&lt;p>So I ran a high-fidelity thematic enrichment pass over 466 sessions from the corpus and started mapping what I&amp;rsquo;m calling the architecture of advice: the hidden patterns that define how AI actually influences a multi-repo technical portfolio.&lt;/p></description></item><item><title>30 days of AI collaboration</title><link>https://thedetech.com/blog/2026-05-07-30-days-of-ai-collaboration/</link><pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate><guid>https://thedetech.com/blog/2026-05-07-30-days-of-ai-collaboration/</guid><description>&lt;p>In the spring of 2026 I spent 30 days living in the &amp;ldquo;jagged frontier&amp;rdquo; of AI-assisted software engineering.&lt;/p>
&lt;p>If you&amp;rsquo;ve worked with Claude Code, Gemini CLI, Cursor, or Codex you know the feeling. A high-intensity session ends, the terminal clears, and months of architectural decisions, debugging insights, and technical pivots vanish with the scrollback. The next morning you remember the &lt;em>outcome&lt;/em> but not the &lt;em>reasoning that got you there&lt;/em>.&lt;/p>
&lt;p>I decided to stop losing that knowledge. This is the data-driven retrospective of 466 sessions, 55,224 turns, and 1,772 technical decisions recovered from a single month of work, and what I found when I went back through the corpus systematically.&lt;/p></description></item></channel></rss>