Simulation testing and evals platform for voice and chat AI agents. Simulate every scenario before launch, score every production call on audio-native metrics.
This is the broad commercial model reported for Roark. Product-level terms are listed below when available.
Trust profile
Roark has introduced a Health Checks feature in its Monitor section, allowing users to track the operational status of voice agents through liveness probes. The update includes a dedicated Health checks page with status-page cards, 30-day uptime reporting, and auto-provisioned dashboard widgets. The system now utilizes a refined liveness check based on agent speech output rather than caller-based heuristics. Additionally, the platform provides cost transparency by detailing probe volume estimates during the configuration process.
Roark has completed a comprehensive redesign and rebuild of its platform, shifting to a metric-led interface intended to surface actionable data more efficiently. The update includes a reconstructed simulation environment built on Customer Flows, the integration of a K-command AI assistant, and persistent user-defined views. The new architecture is designed to support faster project navigation and improved layout consistency across the platform.