<?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 WRITELOOP</title><link>https://writeloop.dev/tags/ai/</link><description>Recent content in AI on WRITELOOP</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 01 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://writeloop.dev/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Creating My Own Deep Research Solution</title><link>https://writeloop.dev/posts/creating-my-own-deep-research-solution/</link><pubDate>Thu, 01 Oct 2026 00:00:00 +0000</pubDate><guid>https://writeloop.dev/posts/creating-my-own-deep-research-solution/</guid><description>&lt;h2 id="the-dillemma"&gt;The Dillemma&lt;/h2&gt;&#10;&lt;p&gt;The deep research tools I tried never quite gave me what I wanted. They produced polished summaries, but when I asked &amp;ldquo;how do you know this?&amp;rdquo; the answer was nowhere in the report, so I set out to build a system whose work I could poke at, trace, and argue with instead of a summary I had to take on faith.&lt;/p&gt;&#10;&lt;p&gt;That system is a deep research skill I built on Hermes, the AI agent I run in an isolated VM on dedicated hardware as my personal assistant. The first versions worked, but they still did not meet the standard I care about, so I kept iterating for the last few months, and only recently has the output reached the point where I genuinely like the reports it hands me (I have even shared some with friends to get some extra opinions). This post is how it works, told the way I came to understand it, one mechanism at a time, and it ends with the checks you can run yourself on any finished report.&lt;/p&gt;</description></item></channel></rss>