Monitor AI configs

Overview

This topic explains how to monitor the performance of your AI configs. Performance metrics for AI configs are available in the LaunchDarkly user interface if you track AI metrics in your SDK.

Monitor an AI config

To monitor the performance of an AI config:

1. Navigate to the detail page for the AI config. Select the Monitoring tab.
2. At the top of the tab, select the environment you want to monitor. Performance metrics are specific to each environment.

• To monitor to an environment that's not shown, click the + icon to add another environment to the Monitoring tab.

3. Review the available metrics:

• Output satisfaction rate is the percentage of "thumbs up" ratings provided by end users who have encountered any version of the AI config in this environment.
• Generation count is the number of successful generations completed using any version of the AI config in this environment.
• Input tokens used is the total input tokens used by all versions of the AI config in this environment.
• Output tokens used is the total output tokens used by all versions of the AI config in this environment.

The data on the Monitoring tab updates approximately each minute. The individual metrics panels indicate recent trends.

Here is an image of the Monitoring tab: