<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Automation on Andrew Healey</title><link>https://healey.io/tags/automation/</link><description>Recent content in Automation on Andrew Healey</description><generator>Hugo -- gohugo.io</generator><language>en-US</language><copyright>© 2026 Andrew Healey</copyright><lastBuildDate>Wed, 05 Aug 2026 08:48:01 -0500</lastBuildDate><atom:link href="https://healey.io/tags/automation/index.xml" rel="self" type="application/rss+xml"/><item><title>When I started building agentic workflows in n8n, I kept running into performance and token consumption problems processing formats like epub, pdf, and the ms office *.docx/pptx/xlsx</title><link>https://healey.io/writing/when-i-started-building-agentic-workflows-in-n8n-i-kept/</link><pubDate>Wed, 05 Aug 2026 08:48:01 -0500</pubDate><guid>https://healey.io/writing/when-i-started-building-agentic-workflows-in-n8n-i-kept/</guid><description>&lt;p&gt;When I started building agentic workflows in n8n, I kept running into performance and token consumption problems processing formats like epub, pdf, and the ms office *.docx/pptx/xlsx. Stripping them down to markdown was the obvious fix since the content mattered more than the form.&lt;/p&gt;&#10;&lt;p&gt;I ended up with a node to process each format into markdown. It dramatically improved accuracy and let me run the better models without sacrificing my credit card (and marriage) over to the token gods, or to use local models without brown outs or melted cables at home.&lt;/p&gt;</description></item><item><title>Hugo Pipeline</title><link>https://healey.io/writing/hugo-pipeline/</link><pubDate>Fri, 13 Feb 2026 23:25:22 -0600</pubDate><guid>https://healey.io/writing/hugo-pipeline/</guid><description>&lt;p&gt;This rebuild has been a long time coming. I finally carved out some time to work through my Obsidian -&amp;gt; Forgejo -&amp;gt; GitHub -&amp;gt; Cloudflare Pages pipeline.&lt;/p&gt;&#10;&lt;p&gt;Obsidian has become my Personal Knowledge Management platform. Editing all the content in the same place I take notes, brainstorm, and organize my life really is a comfortable setup.&lt;/p&gt;&#10;&lt;p&gt;Forgejo has become my playground for automations without incurring the personal costs or data sovereignty concerns over on GitHub. Since this is where my projects live, it only makes sense to keep it there.&lt;/p&gt;</description></item><item><title>Aggregate and Translate: Moving to Google Reader</title><link>https://healey.io/writing/aggregate-and-translate-moving-to-google-reader/</link><pubDate>Sat, 09 Apr 2011 16:15:03 -0500</pubDate><guid>https://healey.io/writing/aggregate-and-translate-moving-to-google-reader/</guid><description>&lt;p&gt;For years, I have been bouncing between &lt;a href="http://www.rssowl.org/" target="_blank" rel="noreferrer"&gt;RSSOwl&lt;/a&gt;, &lt;a href="http://www.feedreader.com/" target="_blank" rel="noreferrer"&gt;FeedReader&lt;/a&gt; and &lt;a href="http://www.feeddemon.com/" target="_blank" rel="noreferrer"&gt;FeedDemon&lt;/a&gt;.  I have built the ultimate feed list for the technologies, blogs and news sources I care about.  The real beauty of RSS is it enables one to quickly get up to date on news and industry trends without wasting time.  New posts are there, you pick the ones that interest you, star or share the ones you care about and ignore the rest.  &lt;strong&gt;While many of my peers are wasting their time hitting all their favorite sites and going page by page, I have already read it and moved on to real work.&lt;/strong&gt;&lt;/p&gt;</description></item></channel></rss>