<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/welcome-to-grokking-llm-evals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/what-an-eval-is</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/why-llm-features-need-evals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-job-ticket-assistant</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/kinds-of-evals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-eval-development-loop</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-what-an-eval-is</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/why-error-analysis-comes-first</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/reading-traces</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/open-coding-notes-on-what-went-wrong</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/axial-coding-from-notes-to-failure-modes</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/counting-and-ranking-failure-modes</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/worked-example-error-analysis-of-120-job-tickets</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-error-analysis-first</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/what-a-test-case-contains</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/sampling-real-traffic</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/generating-synthetic-cases-from-dimensions</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/hard-cases-edge-cases-and-attacks</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/labeling-expected-behavior</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/keeping-a-test-set-useful</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-building-test-sets</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/three-kinds-of-graders</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/code-checks-for-format-and-rules</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/code-checks-that-execute-output</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/comparing-against-a-reference-answer</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/key-fact-checklists</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-code-and-reference-graders</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/how-an-llm-judge-works</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/writing-a-judge-for-one-failure-mode</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/judge-biases</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/validating-a-judge-against-human-labels</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/correcting-a-pass-rate-for-judge-error</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/pairwise-comparisons-and-win-rates</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-llm-judges</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/retrieval-and-generation-as-two-measurements</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/relevance-labels-for-retrieval</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/retrieval-metrics</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/faithfulness-and-groundedness</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/answer-relevance-completeness-and-unanswerable-questions</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/finding-where-a-rag-answer-went-wrong</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-evaluating-rag</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/what-changes-when-the-system-is-an-agent</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/final-state-checks</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/trajectory-checks</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/repeated-runs-and-agent-reliability</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/simulated-users-and-multi-turn-conversations</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/cost-latency-and-step-counts</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-evaluating-agents</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/turning-a-safety-policy-into-test-cases</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/measuring-prompt-injection</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/harmful-requests-and-jailbreaks</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/over-refusal</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/robustness-to-small-input-changes</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/red-teaming-and-the-regression-suite</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-safety-and-robustness</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/a-pass-rate-is-an-estimate</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/confidence-intervals-for-pass-rates</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/how-many-test-cases-you-need</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/comparing-two-versions-on-the-same-cases</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/noise-from-repeated-runs</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/grouped-test-cases-and-clustered-error-bars</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-bootstrap</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/many-comparisons-and-slices</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/writing-an-eval-report</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-statistics-for-evals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/offline-and-online-evaluation</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/evals-as-release-gates</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/logging-traces-for-evaluation</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/grading-sampled-production-traffic</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/guardrails-that-run-on-every-request</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/ab-tests-for-llm-features</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/user-feedback-signals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/drift-and-model-updates</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-evals-in-production</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/what-a-public-benchmark-measures</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/contamination-label-errors-and-saturation</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/leaderboards-and-arena-rankings</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/choosing-a-model-with-your-own-evals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-public-benchmarks-versus-product-evals</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-help-center-bot-and-its-first-error-analysis</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-help-center-test-set</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/help-center-graders-and-judge-validation</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/help-center-release-thresholds</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/monitoring-the-help-center-bot</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-help-center-eval-plan</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-a-help-center-rag-bot</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-upgrade-research-agent</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/research-tasks-with-known-answers</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/grading-claims-citations-and-coverage</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/research-agent-reliability-and-cost</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/injected-instructions-in-fetched-pages</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/the-research-agent-eval-plan</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/chapter-assessment-a-research-agent</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
<url><loc>https://www.designgurus.io/course-play/grokking-llm-evals/doc/final-exam</loc><lastmod>2026-11-10T02:22:28.990Z</lastmod></url>
</urlset>