How-To
Create an Evaluation SetEvaluate and Optimize PromptsEvaluate and Optimize RAG ApplicationsChoose your Guardrail MetricsIdentify HallucinationsRegister Custom MetricsPrompt Management & StorageA/B Compare PromptsExperiment with Multiple PromptsExperiment with Multiple Chain WorkflowsEvaluate with Human FeedbackAdd Tags to Prompt RunsLog Pre-generated ResponsesEvaluate and Optimize Agents, Chains or multi-step workflowsProgrammatically fetch logged dataCollaborate with other personasShare a projectExport your Evaluation RunsUnderstand your metric's values
Last updated