Mike on Data+AI·Jul 25“AI Engineer” Is a Title That No Longer Means AnythingThe work is real. The label is too small for it. What the role actually demands now, and why something like “Intelligence Engineering” may…
RaftLabs·Jun 23Why Your AI Agent Observability Is Lying to You89% of teams have monitoring but only 52% have evaluation. Here’s how to build real testing frameworks.
Nihal Gupta·Feb 10How to Systematically Tune Chunk Size for RAG Systems: A Practical Evaluation FrameworkIntroduction
Himanshu Raj·Apr 24, 2025HypoEval vs G-Eval: A Comparative OverviewOverview of NLG Evaluation Frameworks
InData Science + AI at Microsoftbyshima ghassempour·Mar 4, 2025Beyond thumbs up and thumbs down: A human-centered approach to evaluation design for LLM productsBy Shima GhassemPour, Anna Pershukova, Esra Gokgoz, and Irina NikulinaA response icon1
