Foundry built-in evaluator categories: quality vs RAG vs safety vs agent

This sheet compares General-purpose quality, RAG-specific, Safety and security, Agent-specific.

CriterionGeneral-purpose qualityRAG-specificSafety and securityAgent-specific
MeasuresCoherence and fluency of the textGroundedness and relevance to retrieved contentHate and unfairness, violence, protected materialTool call accuracy and task completion

The verdict, the full comparison, 3 rules and 2 traps are part of AI-103 access. Unlock AI-103.