<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Coding-Agents on Danilo Falcão da Silva</title><link>https://falcao.org/tags/coding-agents/</link><description>Recent content in Coding-Agents on Danilo Falcão da Silva</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 19 May 2026 11:00:00 -0300</lastBuildDate><atom:link href="https://falcao.org/tags/coding-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude Code, opencode, Cursor: My Daily Driver and My Plan B</title><link>https://falcao.org/posts/claude-code-opencode-cursor/</link><pubDate>Tue, 19 May 2026 11:00:00 -0300</pubDate><guid>https://falcao.org/posts/claude-code-opencode-cursor/</guid><description>&lt;p>I&amp;rsquo;ve spent enough of the last six months working alongside an AI coding
agent that I now have actual opinions, in the way you only get from
shipping production code with a tool, not from reading benchmarks
about it. There are three names that dominate the conversation in
2026 and they represent three genuinely different bets about how
humans and language models should collaborate on code.&lt;/p>
&lt;p>This is my honest read on &lt;strong>Cursor&lt;/strong>, &lt;strong>Claude Code&lt;/strong>, and
&lt;strong>opencode&lt;/strong>. The headline:
&lt;strong>Claude Code is my daily driver. opencode is my Plan B. Cursor is
not what I reach for.&lt;/strong> Here&amp;rsquo;s why.&lt;/p></description></item></channel></rss>