<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Software Engineering on Andrew Hunter — Systems Architect &amp; Builder</title>
    <link>https://andrewphunter.com/tags/software-engineering/</link>
    <description>Recent content in Software Engineering on Andrew Hunter — Systems Architect &amp; Builder</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 13 Nov 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://andrewphunter.com/tags/software-engineering/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Architecting with Claude</title>
      <link>https://andrewphunter.com/writing/architecting-with-claude/</link>
      <pubDate>Fri, 13 Nov 2026 00:00:00 +0000</pubDate>
      <guid>https://andrewphunter.com/writing/architecting-with-claude/</guid>
      <description>&lt;p&gt;A coding agent can produce an implementation faster than I can read it carefully. If I respond by spending the rest of the day reviewing every line, I have accelerated one part of development and moved the queue to another. As the volume grows, the temptation is to skim more, trust the test count, and accept the summary. None of that tells me whether we built the right thing.&lt;/p&gt;&#xA;&lt;p&gt;The problem starts earlier than the review. An agent can implement a poor design quite faithfully. It can write tests that preserve the same misunderstanding, then produce a convincing explanation of why they pass. By the time I see the diff, decisions about responsibility, ownership, dependencies, and failure behavior are embedded throughout it. Pulling those decisions back out is expensive work.&lt;/p&gt;&#xA;&lt;p&gt;Anthropic has described this pressure in its own engineering organization. Its &lt;a href=&#34;https://claude.com/resources/articles/code-review&#34;&gt;Code Review announcement&lt;/a&gt; discusses the growing gap between code production and review capacity. Its &lt;a href=&#34;https://claude.com/resources/articles/how-anthropic-secures-its-ai-native-software-development-lifecycle&#34;&gt;account of the development lifecycle&lt;/a&gt; describes combining automated checks and agentic review with human decisions at selected points.&lt;/p&gt;&#xA;&lt;p&gt;The harness around that work includes the context, tools, instructions, checks, and permissions within which an agent works. Claude Code provides the mechanisms. We still have to decide how to use them to develop software we understand and can maintain.&lt;/p&gt;&#xA;&lt;p&gt;&lt;a href=&#34;https://code.claude.com/docs/en/best-practices&#34;&gt;Anthropic&amp;rsquo;s best practices&lt;/a&gt; are a useful foundation: plan the work, give the agent ways to verify it, preserve project knowledge, bound its actions, separate responsibilities, and automate the recurring steps. I use those practices across my own projects. The architectural work is in connecting them, so a decision made during planning survives implementation and can be examined when the result comes back.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
