Create, track, retrieve, update, and delete custom business metrics for AI Configs. Covers full lifecycle: define metric kinds via API, emit events via SDK,…
Custom Metrics for AI Configs Full lifecycle management of custom business metrics: create metric definitions via API, track events via SDK, retrieve metric data, and manage metrics programmatically. Prerequisites LaunchDarkly SDK initialized (see aiconfig-sdk) LaunchDarkly API token with writer role for metric management Understanding of built-in AI metrics (see aiconfig-ai-metrics) API Key Detection Before prompting the user for an API key, try to detect it automatically: Check Claude MCP config - Read ~/.claude/config.json and look for mcpServers.launchdarkly.env.LAUNCHDARKLY_API_KEY Check environment variables - Look for LAUNCHDARKLY_API_KEY, LAUNCHDARKLY_API_TOKEN, or LD_API_KEY Prompt user - Only if detection fails, ask the user for their API key
don't have the plugin yet? install it then click "run inline in claude" again.