ServiceNow Releases EVA Framework for Voice Agent Evaluation

TLDR

ServiceNow-AI has introduced EVA, an end-to-end evaluation framework for conversational voice agents that jointly measures task accuracy and user experience.

Key findings reveal an accuracy-experience tradeoff where agents excelling at task completion tend to provide worse user experiences. The framework and dataset are available on GitHub and Hugging Face.

Key Takeaways

• ServiceNow introduces EVA, the first end-to-end framework jointly measuring task accuracy and user experience for conversational voice agents