<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Hermes on Niall Griffin</title><link>https://griffinai.dev/tags/hermes/</link><description>Recent content in Hermes on Niall Griffin</description><generator>Hugo</generator><language>en-ie</language><lastBuildDate>Mon, 29 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://griffinai.dev/tags/hermes/index.xml" rel="self" type="application/rss+xml"/><item><title>Session brief — Slack, expert agents &amp; GLM</title><link>https://griffinai.dev/sessions/2026-06-29-session-slack-expert-agents-glm/</link><pubDate>Mon, 29 Jun 2026 00:00:00 +0000</pubDate><guid>https://griffinai.dev/sessions/2026-06-29-session-slack-expert-agents-glm/</guid><description>&lt;h1 id="session-brief--29-june-2026"&gt;Session brief — 29 June 2026&lt;/h1&gt;
&lt;p&gt;Covers connecting Hermes to Slack, the design of the first expert-trained domain
agent (neutrality studies, for Prof. Pascal Lottaz), switching the default model
to GLM 5.2, wiring Claude Code to GLM via Coding Helper, and a still-open GLM
authentication bug. Written to be re-read cold: each section states what was done,
why, and what it means.&lt;/p&gt;
&lt;hr&gt;
&lt;h2 id="starting-point"&gt;Starting point&lt;/h2&gt;
&lt;p&gt;Hermes was already running on the Hetzner VPS (91.99.141.162), reachable via
Telegram, with the dashboard accessible over an SSH tunnel, voice transcription
working, and the four-project MEMORY.md in place. Today&amp;rsquo;s goals: add Slack as a
second front door, design the first expert-training agent, and move the default
model to GLM 5.2 for cost.&lt;/p&gt;</description></item></channel></rss>