<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Document Processing on Troy Scott</title><link>https://troyscott.ca/tags/document-processing/</link><description>Recent content in Document Processing on Troy Scott</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sun, 23 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://troyscott.ca/tags/document-processing/index.xml" rel="self" type="application/rss+xml"/><item><title>Designing MarkForge: A Portable, Testable Document Pipeline</title><link>https://troyscott.ca/posts/working-notes/designing-markforge/</link><pubDate>Sun, 23 Aug 2026 00:00:00 +0000</pubDate><guid>https://troyscott.ca/posts/working-notes/designing-markforge/</guid><description>&lt;p&gt;&lt;em&gt;Working Notes are AI-assisted records developed from my project conversations, experiments, and feedback. I review them for accuracy, but they remain provisional and may evolve as I learn.&lt;/em&gt;&lt;/p&gt;&#10;&lt;p&gt;&lt;a href="https://github.com/troyscott/markforge"&gt;MarkForge is an open-source, local document-to-Markdown pipeline&lt;/a&gt; designed to run on a portable Apple Silicon MacBook Air as well as Windows systems with NVIDIA acceleration. It converts PDFs and Office documents into structured Markdown, extracted images, and manifests that record how the work was performed.&lt;/p&gt;</description></item></channel></rss>