Amazon Connect introduces new metrics to enhance AI agent performance

Amazon Connect has introduced eight new metrics designed to assess and enhance the performance of AI agents. These metrics include the goal success rate, faithfulness score, and tool selection accuracy, among others. The introduction of these metrics aims to provide greater insight into the quality of AI-driven customer interactions, thereby facilitating the measurement and continuous improvement of AI agent outcomes.

With these new tools, users can monitor whether AI agents are effectively resolving customer requests, assess the faithfulness of responses, and identify any contextual inaccuracies. Additionally, the metrics allow for the evaluation of tool selection and utilization accuracy. Customer feedback can also be captured through thumbs up or down ratings, if this feature is enabled.

These metrics can be accessed via the AI Agent Performance dashboard within Amazon Connect. Alternatively, users can retrieve data through the GetMetricDataV2 API or utilize the zero-ETL data lake for custom reporting or integration with existing analytics workflows.

This new feature is available in all AWS Regions that support Amazon Connect AI Agents. For more detailed information, users are encouraged to refer to the Amazon Connect Administrator Guide. To explore more about Amazon Connect, which is an AI-native solution designed to transform every customer interaction into a memorable experience, please visit the Amazon Connect website.