EvalOps / LLM Reliability

Reliability Console

Prompt, model, dataset, and grader regression testing.

DashboardDatasetsPromptsRunsNew evaluationCompare

Prompts

Prompt versions

Baseline and intentionally degraded prompt versions used for regression comparisons across workflows.

NameWorkflowVersionCreated
incident_triage_baselineincident_triagev1Aug 5, 2026, 8:04 p.m.
incident_triage_degradedincident_triagev1-degradedAug 5, 2026, 8:04 p.m.
rag_qa_baselinerag_qav1Aug 5, 2026, 8:04 p.m.
rag_qa_degradedrag_qav1-degradedAug 5, 2026, 8:04 p.m.
support_classification_baselinesupport_classificationv1Aug 5, 2026, 8:04 p.m.
support_classification_degradedsupport_classificationv1-degradedAug 5, 2026, 8:04 p.m.