← Back to integrations

Workflow Integration

Experiment Tracking

03

Weights & Biases and MLflow metadata align experiments with EvalOps scorecards.

Overview

Sync your ML experiment tracking with EvalOps evaluation workflows. Connect prompt experiments to W&B runs, track evaluations alongside model metrics, and maintain a complete history of your AI development.

Key Features

Weights & Biases integration

MLflow tracking server support

Experiment metadata sync

Evaluation run linking

Artifact management

Comparison dashboards

Capabilities

Experiment-to-evaluation mapping

Historical comparison

Hyperparameter correlation

Artifact versioning

Team collaboration

Use Cases

01

Track prompt engineering experiments

02

Compare model performance over time

03

Correlate hyperparameters with quality

04

Share experiment results team-wide

Getting Started

Configure W&B or MLflow credentials. Link experiments to EvalOps workspaces. Start tracking evaluations alongside training runs.