<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Genai on Nicole van der Hoeven</title><link>https://nicolevanderhoeven.com/tags/genai/</link><description>Recent content in Genai on Nicole van der Hoeven</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><copyright>Nicole van der Hoeven</copyright><lastBuildDate>Wed, 21 Jan 2026 16:00:00 +0100</lastBuildDate><atom:link href="https://nicolevanderhoeven.com/tags/genai/index.xml" rel="self" type="application/rss+xml"/><item><title>Observability for GenAI Applications (Grafana ❤️🔥 OpenTelemetry Community Call #4)</title><link>https://nicolevanderhoeven.com/blog/20260121-gocc04-observability-for-genai-applications/</link><pubDate>Wed, 21 Jan 2026 16:00:00 +0100</pubDate><guid>https://nicolevanderhoeven.com/blog/20260121-gocc04-observability-for-genai-applications/</guid><description>&lt;p&gt;In this community call with my coworker Liudmila Molkova, we dove into the emerging field of observability for Generative AI applications. We explored how to instrument LLM-powered applications using OpenTelemetry, what metrics and traces matter most when monitoring AI workloads, and how to debug issues in complex AI pipelines. The discussion covered prompt tracing, token usage monitoring, latency considerations, and the unique challenges of observing non-deterministic AI systems.&lt;/p&gt;
&lt;div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;"&gt;
&lt;iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" loading="eager" referrerpolicy="strict-origin-when-cross-origin" src="https://www.youtube.com/embed/LfDVygRWQJU?autoplay=0&amp;amp;controls=1&amp;amp;end=0&amp;amp;loop=0&amp;amp;mute=0&amp;amp;start=0" style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;" title="YouTube video"&gt;&lt;/iframe&gt;
&lt;/div&gt;</description></item></channel></rss>