<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>AI on Dakotah Peña</title>
    <link>https://dakotahpena.dev/tags/ai/</link>
    <description>Recent content in AI on Dakotah Peña</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <copyright>© Dakotah Peña</copyright>
    <lastBuildDate>Sat, 11 Jul 2026 09:05:32 -0700</lastBuildDate>
    <atom:link href="https://dakotahpena.dev/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Save YouTube Video Learnings to Obsidian</title>
      <link>https://dakotahpena.dev/posts/save-youtube-learnings-to-obsidian/</link>
      <pubDate>Sat, 11 Jul 2026 09:05:32 -0700</pubDate>
      <guid>https://dakotahpena.dev/posts/save-youtube-learnings-to-obsidian/</guid>
      <description>&lt;p&gt;I use the note-taking app Obsidian for my personal organization needs, and over time I&amp;rsquo;ve been building it to function as a second brain. Since Obsidian is built around markdown files on the file system, there&amp;rsquo;s no vendor lock-in, and it&amp;rsquo;s very easy to use with AI models for reading and writing to it. This has led me to optimize how I retain information that I want to remember.&lt;/p&gt;&#xA;&lt;p&gt;Occasionally, I&amp;rsquo;ll watch an inspiring YouTube video that teaches me something useful. Bookmarking the link is futile because no knowledge is retained, and I would almost never go back into my bookmarks and watch it again. The experience was mostly ephemeral. Not wanting interesting content to be transitory, I set out to build a skill that distills the learning from the video&amp;rsquo;s audio into an Obsidian note that&amp;rsquo;s easy to re-read in the future. The cleaned-up note becomes part of my knowledge base to inspire me and help me learn from the content.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Agentic Coding Demands a Higher Code Quality Baseline</title>
      <link>https://dakotahpena.dev/posts/agentic-coding-code-quality-baseline/</link>
      <pubDate>Fri, 10 Jul 2026 09:22:14 -0700</pubDate>
      <guid>https://dakotahpena.dev/posts/agentic-coding-code-quality-baseline/</guid>
      <description>&lt;p&gt;The age of agentic coding requires a greater focus on the baseline of code quality.&lt;/p&gt;&#xA;&lt;p&gt;In the past, great developers often had a mindset of leaving something better than they found it. In the slack time between ticket estimates, engineers would often dedicate time to refactor something that had grown stale, alongside pushing new development forward.&lt;/p&gt;&#xA;&lt;p&gt;Today, code is generated quickly and cheaply, with more focus given to pushing new development forward at a blistering pace. This leaves less time to evaluate the quality of existing code for opportunities to improve it. I have found that the biggest impact on agentic code quality is the existing code quality, with AGENTS.md, prompts, and skills having much less of an impact than what is already in place.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
