Platform for building, running, and managing AI agents and multi-agent workforces at scale.
This is the broad commercial model reported for Relevance AI. Product-level terms are listed below when available.
Trust profile
No compliance claims have been published for this company.
Relevance AI has introduced 'Evals,' an automated testing and evaluation feature for AI agents and workforces. The tool allows users to create scenario-based test sets, define custom evaluation criteria using 'Checks' (such as LLM performance, output content, and tool usage), and monitor the quality of live agent interactions through dashboards. Evals aims to provide a reliable command center for testing agent behavior and performance before deployment, with the ability to block publishing if evaluation scores do not meet predefined pass-rate thresholds.