<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Planning on Jason Craft</title><link>https://www.jasoncraft.org/workbench/tags/planning/</link><description>Recent content in Planning on Jason Craft</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 30 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.jasoncraft.org/workbench/tags/planning/index.xml" rel="self" type="application/rss+xml"/><item><title>Co-Writing a Novel With an Agent: The Showrunner Model</title><link>https://www.jasoncraft.org/workbench/posts/02-showrunner-model/</link><pubDate>Mon, 30 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.jasoncraft.org/workbench/posts/02-showrunner-model/</guid><description>&lt;p&gt;This is the second post in a series about the systems I&amp;rsquo;ve built to co-write a &amp;ldquo;meganovel&amp;rdquo; (targeting 1,000,000 words or more) with an AI agent. The &lt;a href="https://www.jasoncraft.org/workbench/posts/01-context-management/"&gt;first post&lt;/a&gt; covers the context management problem and the search/MCP tooling I built to solve it. This one is about how we plan together, how I think about the collaboration, and the architectural contract that keeps the robot from surfacing things it shouldn&amp;rsquo;t.&lt;/p&gt;
&lt;p&gt;If you&amp;rsquo;ve used an agentic coding tool, you probably have picked up the flow of gathering context, building a structured understanding of the problem, producing a spec, then letting the agent execute autonomously from the spec. I use the same process to write chapters of a novel. The &amp;ldquo;problem&amp;rdquo; is a chapter. The &amp;ldquo;spec&amp;rdquo; is a beat sheet with dialogue intent and character notes. It&amp;rsquo;s a little more fun than a software spec (although some engineers might say the opposite), but it&amp;rsquo;s more the same than not.&lt;/p&gt;</description></item></channel></rss>