<?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>Azure AI Foundry on KiwiGPT</title><link>https://www.kiwigpt.co.nz/tags/azure-ai-foundry/</link><description>Recent content in Azure AI Foundry on KiwiGPT</description><generator>Hugo -- 0.148.2</generator><language>en-us</language><lastBuildDate>Fri, 15 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.kiwigpt.co.nz/tags/azure-ai-foundry/index.xml" rel="self" type="application/rss+xml"/><item><title>How I Got Prompt Engineering Wrong</title><link>https://www.kiwigpt.co.nz/posts/how-i-got-prompt-engineering-wrong/</link><pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate><guid>https://www.kiwigpt.co.nz/posts/how-i-got-prompt-engineering-wrong/</guid><description>Why simple prompts sometimes outperform complex ones, and how chat apps, APIs, and local LLMs all respond differently.</description></item></channel></rss>