<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Beyond Copilot / Reflective on 💻✨ AI for Coding</title><link>https://kjetiljd.github.io/ai-for-coding/categories/beyond-copilot-/-reflective/</link><description>Recent content in Beyond Copilot / Reflective on 💻✨ AI for Coding</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 08 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kjetiljd.github.io/ai-for-coding/categories/beyond-copilot-/-reflective/index.xml" rel="self" type="application/rss+xml"/><item><title>Tip #45: Don't wait for a "harness engineering team"</title><link>https://kjetiljd.github.io/ai-for-coding/tips/045-dont-wait-for-harness-team/</link><pubDate>Wed, 08 Jul 2026 00:00:00 +0000</pubDate><guid>https://kjetiljd.github.io/ai-for-coding/tips/045-dont-wait-for-harness-team/</guid><description>Your agent = model + harness. Centralising the harness in a dedicated team likely repeats the DevOps-team mistake — the friction of each team building its own is where the learning happens.</description></item></channel></rss>