ZZahiruddin Tavargere·Nov 9How DoorDash knew its AI agent got worseDoorDash had a production agent running on Claude Sonnet 4.6.3 min read·zahere.com
HHéctor Arriola·Sep 19, 2025AI Evals, Without the Jargon: How We’re Keeping Our Agents Honest at our AgencyDatasets, rubrics, LLM judges, and the scoring system we use to catch regressions before our customers do. Plus a copy-paste rubric to get you started.6 min read·hectorarriola.com
Ggyani·Jun 23, 2025Debiasing LLM Judges: Understanding and correcting AI Evaluation BiasExplore how to correct biases in AI evaluations and improve model accuracy using debiasing techniques for large language models as judges (LLM-as-a-judge)6 min read·allthingsproduct.hashnode.dev