aiconfig-ai-metrics

Name: aiconfig-ai-metrics
Availability: InStock
Author: LaunchDarkly

Instrument LaunchDarkly AI Config calls to capture duration, tokens, and success/error metrics.

25|8|Updated Feb 3, 2026

Search Tags:#monitoring #python #metrics #instrumentation #tracking #node #aiconfig

Ready to run

npx skills add https://github.com/launchdarkly/ai-tooling --skill aiconfig-ai-metrics-launchdarkly

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: aiconfig-ai-metrics
Source: https://github.com/launchdarkly/ai-tooling/tree/main/skills/ai-configs/aiconfig-ai-metrics
Command: npx skills add https://github.com/launchdarkly/ai-tooling --skill aiconfig-ai-metrics-launchdarkly

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Instrument LaunchDarkly AI Config calls with automated metrics collection, surfacing duration, token usage, and success/error data for observability and reliability.

Core Features & Use Cases

Four-tier instrumentation ladder (managed runner, provider package, custom extractor, and raw manual) across Python and Node.
Wrap calls with trackMetricsOf or implement a manual Tier-4 path to ensure Monitoring data is captured for any provider.
Use the metrics to validate deployments, troubleshoot failures, and improve AI Config-based pipelines and tooling.

Quick Start

Wrap an AI Config call with the tracker using an appropriate tier, then verify metrics appear in the Monitoring tab.

Frequently Asked Questions about aiconfig-ai-metrics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I instrument LaunchDarkly AI Config calls for metrics tracking?▼

To instrument AI Config calls for metrics tracking, wrap your provider calls using the trackMetricsOf function or implement a manual Tier-4 path. This automatically captures duration, token usage, and success or error data for observability.

What is the four-tier instrumentation ladder for AI Config metrics?▼

The four-tier instrumentation ladder for AI Config metrics provides escalating abstraction levels: managed runner, provider package, custom extractor with trackMetricsOf, and raw manual tracking. It ensures monitoring data is captured for any provider type in Python and Node environments.

Can I track AI Config duration and tokens in both Python and Node environments?▼

Yes, you can track AI Config duration and tokens in both Python and Node environments. The instrumentation ladder applies across multiple provider types in both languages, allowing you to wrap calls and flush metrics to ensure monitoring visibility.

How do I ensure metrics are visible when config.enabled is checked?▼

To ensure metrics are visible when config.enabled is checked, respect the config.enabled checks during your wrapped calls and explicitly flush metrics after execution. This guarantees that monitoring data is successfully captured and sent to the Monitoring tab.

What is the best way to capture success and error metrics for AI Config pipelines?▼

The best way to capture success and error metrics for AI Config pipelines is using the trackMetricsOf wrapper or the manual Tier-4 pattern. This approach validates deployments, troubleshoots failures, and improves tooling with minimal toil.