<?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>Claude on Joshua's Notebook</title><link>https://burnett.sh/tags/claude/</link><description>Recent content in Claude on Joshua's Notebook</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 18 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://burnett.sh/tags/claude/index.xml" rel="self" type="application/rss+xml"/><item><title>HoneyPi: A Sample AI-Generated Threat Report</title><link>https://burnett.sh/posts/honeypi-sample-report/honeypi-sample-ai-report/</link><pubDate>Thu, 18 Jun 2026 00:00:00 +0000</pubDate><guid>https://burnett.sh/posts/honeypi-sample-report/honeypi-sample-ai-report/</guid><description>&lt;blockquote&gt;
&lt;p&gt;I wanted to post a sample of the AI-Generated reporting that I was able to achieve with
only a little bit of tweaking to the prompts in the base script. The value add here for
someone in my position with limited time and resources is incredible. My next
implementation of this, will be internal focused on that Security Onion stack and the
report will be directed at what I need to address daily on my internal assets.&lt;/p&gt;</description></item><item><title>HoneyPi Part 6: AI Reporting</title><link>https://burnett.sh/posts/honeypi-enrich-ai/</link><pubDate>Wed, 17 Jun 2026 10:00:00 -0500</pubDate><guid>https://burnett.sh/posts/honeypi-enrich-ai/</guid><description>&lt;p&gt;The &lt;a href="https://burnett.sh/posts/honeypi-enrich-pi/"&gt;previous two&lt;/a&gt; &lt;a href="https://burnett.sh/posts/honeypi-enrich-mac/"&gt;posts&lt;/a&gt; got all three streams into Loki, unified by &lt;code&gt;src_ip&lt;/code&gt; and joinable by Community ID. That&amp;rsquo;s a powerful dataset, but it has a problem: it&amp;rsquo;s enormous. A single day produces tens of thousands of Cowrie events, thousands of Suricata alerts, and thousands of Zeek records. Nobody is reading that by hand every morning. This post covers the layer that makes the whole thing usable, a Python script that pulls the day&amp;rsquo;s data, scores attackers by how interesting they are, and hands the most significant ones to Claude to write up as per-attacker narratives.&lt;/p&gt;</description></item></channel></rss>