<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tooling on Alex Herrero</title><link>https://alexherrero.dev/tags/tooling/</link><description>Recent content in Tooling on Alex Herrero</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sat, 06 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://alexherrero.dev/tags/tooling/index.xml" rel="self" type="application/rss+xml"/><item><title>The multi-surface wall</title><link>https://alexherrero.dev/thoughts/the-multi-surface-wall/</link><pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate><guid>https://alexherrero.dev/thoughts/the-multi-surface-wall/</guid><description>&lt;p&gt;The dream for Agent M is one agent everywhere — same personality, same memory, same workflows, whatever tool I happen to be in. In practice I get most of the way there: it runs the same across Claude Code and Antigravity, and can read its memory from a couple of other surfaces. But it&amp;rsquo;s not there yet. Chat-only assistants can&amp;rsquo;t touch live files, so they&amp;rsquo;re out for actual work. And not every tool lets a setup like mine install its own hooks or scheduling — on some, my guardrails can watch but can&amp;rsquo;t act. So today I learned that &amp;ldquo;works everywhere&amp;rdquo; has an asterisk right now: the agent travels, but the surfaces underneath are uneven, and the portable, do-anything agent is getting closer, but probably still a harness generation away.&lt;/p&gt;</description></item></channel></rss>