Evaluation framework for LLM knowledge inputs — prompts, RAG corpora, skills, agent workflows. Fix the model, vary the artifact. Built-in statistical rigor: bootstrap CI, Krippendorff α, length-debias, saturation curves.
benchmark ai evaluation-framework claude knowledge-engineering skill-evaluation llm prompt-engineering prompt-testing llm-evaluation rag-evaluation llm-judge claude-code agent-evaluation bootstrap-ci krippendorff-alpha evaluation-as-code multi-judge-ensemble
-
Updated
May 30, 2026 - TypeScript