Evaluation & observability
Golden datasets, LLM-as-judge and its known biases, and tracing a multi-step run transfer across every tool. This is the most under-invested cluster in the domain.
Layer 35 entities0 started
Entities
Section titled “Entities”langsmith
Not started. Becomes a package with its own syllabus once it begins.
langfuse
Not started. Becomes a package with its own syllabus once it begins.
ragas
Not started. Becomes a package with its own syllabus once it begins.
promptfoo
Not started. Becomes a package with its own syllabus once it begins.
braintrust
Not started. Becomes a package with its own syllabus once it begins.