<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>How Can I Use Agents? on Butterswords | Where Words &gt;= Swords</title><link>https://butterswords.com/series/how-can-i-use-agents/</link><description>Recent content in How Can I Use Agents? on Butterswords | Where Words &gt;= Swords</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 06 Jul 2026 13:05:37 -0700</lastBuildDate><atom:link href="https://butterswords.com/series/how-can-i-use-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>A Few Reflections as a Product Manager Building a Demo Using the Claude system</title><link>https://butterswords.com/blog/building-demos-using-claude/</link><pubDate>Mon, 06 Jul 2026 13:05:37 -0700</pubDate><guid>https://butterswords.com/blog/building-demos-using-claude/</guid><description>&lt;div class="bg-tlgray-200/40 border-l-4 border-blue-600 px-6 py-4 mb-8"&gt;
&lt;strong&gt;BLUF:&lt;/strong&gt; Requirements engineering has increased in importance in challenging ways at the pace of &lt;em&gt;AI&lt;/em&gt;. Learn from those who came before. Adapt what exists to your context and needs. It's on those of us who design and build products and systems to find the path forward. We must not pretend the use cases are so novel, or that we are so smart, as to be the only ones who can figure it out.
&lt;/div&gt;
&lt;p&gt;One company I interviewed for asked me to build a demo over the course of a week. They chose a problem space central to their mission, and which I knew very little about. They gave me the assignment on Monday morning, and wanted me to complete it within 5 business days. I gave myself the goal of getting it done by Friday night so I could enjoy Father&amp;rsquo;s Day with my son. This meant I had under 5 business days to research, design, and implement the demo. I then had to record a 10 minute demo and prepare for a follow up debrief. I decided to use the Claude systems to organize and execute the project because of a conversation with a friend about the &lt;a href="%22blog/agent-usefulness.md%22"&gt;usefulness of agents&lt;/a&gt; . It felt like a good, &amp;ldquo;core&amp;rdquo; use case to explore.&lt;/p&gt;</description></item><item><title>Starting to evaluate agent usefulness</title><link>https://butterswords.com/blog/agent-usefulness/</link><pubDate>Wed, 24 Jun 2026 09:54:49 -0700</pubDate><guid>https://butterswords.com/blog/agent-usefulness/</guid><description>&lt;p&gt;I recently talked with a friend and collaborator about agents and the usefulness of products such as Anthropic&amp;rsquo;s Claude (incl. Cowork and Claude Code). We did not agree on much during the conversation, with me sounding very rigid and curmudgeonly and him taking on an optimistic view I did not expect. I respect this person a great deal, so as he continued to argue for the benefits and usefulness of these systems in his life I felt a desire to better understand where he was coming from. Towards the end of the conversation he gave me a blanket challenge:&lt;/p&gt;</description></item></channel></rss>