skills.rest
dominodatalab
dominodatalabOFFICIAL
Explore all skills by this author →
WebsiteGitHub

domino-genai-tracing

Traces ML model runs and manages the model lifecycle in MLflow.

6|3|Updated Feb 19, 2026
Search Tags:#llm#evaluation#tracing#mlflow#genai#domino sdk
One-click install
npx skills add https://github.com/dominodatalab/domino-claude-plugin --skill domino-genai-tracing-dominodatalab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: domino-genai-tracing
Source: https://github.com/dominodatalab/domino-claude-plugin/tree/main/skills/genai-tracing
Command: npx skills add https://github.com/dominodatalab/domino-claude-plugin --skill domino-genai-tracing-dominodatalab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mlflow, dominodatalab, openai, anthropic, langchain, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides comprehensive capabilities to trace, debug, and evaluate Generative AI applications, ensuring reliability and performance in complex LLM-powered systems.

Core Features & Use Cases

  • End-to-End Tracing: Automatically captures LLM calls, agent interactions, RAG pipelines, and multi-step AI workflows.
  • Performance Monitoring: Tracks token usage, latency, cost, and errors for each component.
  • Evaluation Framework: Supports custom evaluators and LLM-as-judge for quality assessment.
  • Use Case: Debug a multi-agent system by visualizing the trace of each agent's interaction, identifying bottlenecks, and evaluating the quality of the final output.

Quick Start

Use the domino-genai-tracing skill to trace a function named 'my_agent' that uses the OpenAI API.

Frequently Asked Questions about domino-genai-tracing

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

FAQPage Schema
How do I trace and evaluate GenAI applications using MLflow?▼

To trace and evaluate GenAI applications with MLflow, use this Skill to capture telemetry like token usage, latency, and errors for LLM interactions, while supporting LLM-as-judge evaluators and custom metrics for performance analysis.

What telemetry is captured when tracing LLM interactions in Domino Data Lab?▼

Tracing LLM interactions in Domino Data Lab captures detailed telemetry including token usage, latency, cost, tool calls, and errors for agents, RAG pipelines, and multi-step AI workflows using the Domino SDK and MLflow.

Can I use MLflow to debug a multi-agent system and evaluate output quality?▼

Yes, you can use MLflow to debug a multi-agent system by visualizing the trace of each agent's interaction, identifying bottlenecks, and evaluating the quality of the final output using LLM-as-judge evaluators.

Does this tracing skill work with LangChain, OpenAI, and Anthropic frameworks?▼

Yes, this tracing skill works with LangChain, OpenAI, and Anthropic frameworks, enabling comprehensive end-to-end tracing and evaluation of Generative AI applications within the Domino Data Lab environment.

How do I evaluate RAG pipelines and track costs for LLM calls?▼

You evaluate RAG pipelines and track costs for LLM calls by capturing detailed telemetry across multi-step AI workflows, automatically monitoring token usage, latency, and expenses for each component using MLflow.

Related Skills

Explore More Software Engineering Skills→
ToXMonToXMon

domino-modeling-assistant

Execute Domino jobs and manage project files via MCP integration.

Community
Advanced
teegin-gteegin-g

agent-evaluation

Evaluate and optimize LLM agent outputs using MLflow APIs.

Community
Advanced
hoodinihoodini
262

langchain

Build end-to-end LLM applications with LangChain and LangGraph.

Community
Advanced
JingyiWngJingyiWng

querying-mlflow-metrics

Fetch aggregated MLflow trace metrics for token counts, latency, and assessment scores.

Community
Intermediate