<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Smol on Jettro Coenradie</title><link>https://coenradie.com/tags/smol/</link><description>Recent content in Smol on Jettro Coenradie</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Jettro Coenradie</copyright><lastBuildDate>Mon, 16 Nov 2026 08:00:00 +0100</lastBuildDate><atom:link href="https://coenradie.com/tags/smol/index.xml" rel="self" type="application/rss+xml"/><item><title>Give your agent a sandbox: tool calls, Monty and Smol compared</title><link>https://coenradie.com/posts/improving-agents-with-sandboxes-monty-and-smol/</link><pubDate>Mon, 16 Nov 2026 08:00:00 +0100</pubDate><guid>https://coenradie.com/posts/improving-agents-with-sandboxes-monty-and-smol/</guid><description>Run the same whisky-tasting agent with ordinary tool calls, with Code Mode in Monty, and with a Smol microVM, and measure when letting the agent write code actually pays off.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://coenradie.com/posts/improving-agents-with-sandboxes-monty-and-smol/featured.png"/></item></channel></rss>