Mosaic AI Agent Evaluation

Product

Evaluation system using human feedback, built-in metrics and LLM judges to measure generative-AI and agent quality.

Releases

Mar 12, 2025Agent Evaluation gains customizable metrics and open tracingMosaic AI Agent EvaluationFeature update

Databricks enhanced agent evaluation with customizable LLM judges, human review workflows and OpenTelemetry-based MLflow tracing.

Jun 28, 2023Mosaic AI Agent Evaluation introducedMosaic AI Agent EvaluationProduct launch

Databricks introduced automated and human evaluation tooling for assessing generative-AI quality on enterprise data.