<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents on Thede Technologies</title><link>https://thedetech.com/tags/agents/</link><description>Recent content in Agents on Thede Technologies</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 06 Aug 2026 19:08:20 -0500</lastBuildDate><atom:link href="https://thedetech.com/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>An Agent Reads My Email</title><link>https://thedetech.com/blog/2026-08-06-an-agent-reads-my-email/</link><pubDate>Thu, 06 Aug 2026 00:00:00 +0000</pubDate><guid>https://thedetech.com/blog/2026-08-06-an-agent-reads-my-email/</guid><description>&lt;p>Every morning at five, an agent reads yesterday&amp;rsquo;s email and writes me a briefing. Most mornings I read the briefing instead of the inbox.&lt;/p>
&lt;p>My friend Kyle Reinford just published &lt;a href="https://kyledeanreinford.com/blog/cloudflare-email-workers-for-llm-pipeline/" target="_blank" rel="noopener noreferrer">the pattern he uses&lt;/a>
 - Cloudflare Email Workers catch messages at the edge and file them into R2, so a model never touches his real Gmail. Mine is the same idea from the other end: he guards the front door, I process at home. Apple Mail already syncs my accounts to disk. A script reads the last 24 hours of messages and hands each body to a local model - Qwen3.6-35b-a3b, running in LM Studio on my Mac Studio. No agent harness, no tool loop - just one chat call to localhost per message. All the model gets to do is fill out a tiny form: what is this, does it need me, one-line summary. A renderer turns the day&amp;rsquo;s forms into a static page. Nothing leaves the house.&lt;/p></description></item></channel></rss>