0
2.0.2
Australia Patch 2, Zurich Patch 9, Zurich Patch 8, Zurich Patch 5
Standalone Application
AI Control Tower – Evaluations provides insight into the runtime executions of AI agents by generating scores and detailed reasoning through an LLM-as-a-judge. It produces average quality and safety scores for each agent and tracks performance trends over time.
- Generates scores and detailed reasoning using an LLM-as-a-judge.
- Produces average quality and safety scores for each agent.
- Tracks performance trends over time.
New:
- Provides actionable insights into the runtime executions of AI agents
- Support multiple scoring providers
- Ability to enable/disable evaluations at AI agent level
Plugin Dependencies:
- com.glide.hub.etl_consumer.kafka
App Dependencies:
- sn_ai_governance (6.2.5)
- sn_ai_metric_ui (1.2.1)
- sn_telemetry_data (1.1.12)
- sn_skill_builder (8.2.9)
Other app dependencies to support evaluations for third-party agents:
- sn_ai_disc (2.0.6)