<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Fran Canete — Notes</title><description>Notes on building software with coding agents, Claude Code, and practical AI-assisted development workflows.</description><link>https://francanete.com/</link><item><title>My Claude Code setup.</title><link>https://francanete.com/notes/claude-code-workflow/</link><guid isPermaLink="true">https://francanete.com/notes/claude-code-workflow/</guid><description>A static note on how I keep my coding-agent workflow version-controlled: prompts, commands, conventions, and the review loop that makes Claude Code useful day to day.</description><pubDate>Sun, 31 May 2026 00:00:00 GMT</pubDate></item><item><title>My Pi agent setup.</title><link>https://francanete.com/notes/pi-agent-workflow/</link><guid isPermaLink="true">https://francanete.com/notes/pi-agent-workflow/</guid><description>A static note on how I am starting to use Pi as my coding-agent harness: the model defaults, subagents, memory, web tools, and the small workflow rules that make it useful.</description><pubDate>Sun, 31 May 2026 00:00:00 GMT</pubDate></item><item><title>How I keep coding agents honest.</title><link>https://francanete.com/notes/keep-coding-agents-honest/</link><guid isPermaLink="true">https://francanete.com/notes/keep-coding-agents-honest/</guid><description>A static note on my review loop for AI-generated code: using cold validators, scoped reviews, evidence, and fresh-context subagents before I trust the work.</description><pubDate>Sun, 31 May 2026 00:00:00 GMT</pubDate></item></channel></rss>