Compare answers against a stated rubricJudge specific requirements against a reference without inventing an overall quality score.evaluationmodel-comparisongrounding
Extract fields without guessingReturn a small JSON record with evidence for each value and null for information the source does not provide.jsonextractiongrounding
Summarise a source, keep its caveatsProduce a short summary that preserves denominators, uncertainty and the limits of the supplied evidence.summarisationgroundingevaluation
Retrieval-Augmented Generation (RAG)A technique that grounds LLM responses in external data by retrieving relevant documents before generating a reply.3 Apr 2026architectureretrievalllmgrounding