<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/ef94e80d0a214323a9f0640b5d9e476c&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/ef94e80d0a214323a9f0640b5d9e476c-e032e50a8de2f7e7.gif</thumbnail_url><duration>3603.537</duration><title>Using AI Agents for Character Dialogue Scenes</title><description>I walked through agentic AI using Claude and ChatGPT, especially how to generate better character dialogue by giving sub agents separate character sheets and running the scene across multiple turns. I also warned against giving AI access to sensitive email or using overly broad goals, since misalignment and weird behavior can happen. I demoed a multi agent scene draft and showed how I track character sheets in Obsidian. I mentioned upcoming classes like Agentic SDLC and Active Fiction, and invited you to join the campus hackathon this weekend to help test. No other specific action was requested besides joining and showing up.</description></oembed>