<?xml version="1.0" encoding="utf-8" standalone="yes"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml"><url><loc>https://datatweets.com/courses/llm-evaluation/evaluating-agents-and-tool-use/lesson-1-why-agents-are-harder-to-evaluate/</loc><lastmod>2026-07-07T09:00:00+02:00</lastmod><changefreq>monthly</changefreq><priority>0.5</priority></url><url><loc>https://datatweets.com/courses/llm-evaluation/evaluating-agents-and-tool-use/lesson-2-task-success-and-outcome-metrics/</loc><lastmod>2026-07-07T09:00:00+02:00</lastmod><changefreq>monthly</changefreq><priority>0.5</priority></url><url><loc>https://datatweets.com/courses/llm-evaluation/evaluating-agents-and-tool-use/lesson-3-tool-call-correctness/</loc><lastmod>2026-07-07T09:00:00+02:00</lastmod><changefreq>monthly</changefreq><priority>0.5</priority></url><url><loc>https://datatweets.com/courses/llm-evaluation/evaluating-agents-and-tool-use/lesson-4-trajectory-evaluation/</loc><lastmod>2026-07-07T09:00:00+02:00</lastmod><changefreq>monthly</changefreq><priority>0.5</priority></url><url><loc>https://datatweets.com/courses/llm-evaluation/evaluating-agents-and-tool-use/lesson-5-guided-project-evaluating-an-agentic-docent/</loc><lastmod>2026-07-07T09:00:00+02:00</lastmod><changefreq>monthly</changefreq><priority>0.5</priority></url></urlset>