<?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>Openai on Harry Kimpel</title><link>https://www.kimpel.com/tags/openai/</link><description>Recent content in Openai on Harry Kimpel</description><image><title>Harry Kimpel</title><url>https://cdn.kimpel.com/og-default.png</url><link>https://cdn.kimpel.com/og-default.png</link></image><generator>Hugo -- 0.164.0</generator><language>en-us</language><lastBuildDate>Mon, 13 Jul 2026 11:08:49 +0000</lastBuildDate><atom:link href="https://www.kimpel.com/tags/openai/index.xml" rel="self" type="application/rss+xml"/><item><title>Monitoring AI/LLM Applications with New Relic: Token Usage, Cost, and Model Comparison</title><link>https://www.kimpel.com/2026/07/13/monitoring-ai-llm-applications-with-new-relic/</link><pubDate>Mon, 13 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.kimpel.com/2026/07/13/monitoring-ai-llm-applications-with-new-relic/</guid><description>What I learned running AI monitoring workshops: how to instrument a Python OpenAI app with New Relic, what metrics matter in production LLM apps, and how to compare GPT models on cost and quality.</description></item></channel></rss>