<?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>Langfuse on Jack Monte — AI Engineer</title><link>https://jackmonte.com/tags/langfuse/</link><description>Recent content in Langfuse on Jack Monte — AI Engineer</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 28 May 2026 21:45:00 -0700</lastBuildDate><atom:link href="https://jackmonte.com/tags/langfuse/index.xml" rel="self" type="application/rss+xml"/><item><title>My Eval Dashboard Showed 1 Trace. I Expected 120.</title><link>https://jackmonte.com/posts/why-my-eval-dashboard-showed-one-trace/</link><pubDate>Thu, 28 May 2026 21:45:00 -0700</pubDate><guid>https://jackmonte.com/posts/why-my-eval-dashboard-showed-one-trace/</guid><description>Adding Langfuse observability to a RAG pipeline looked done until the dashboard showed a single trace and zero scores. The fix was about trace structure, not the SDK. Here is the gotcha, the fix, and the numbers.</description></item></channel></rss>