> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/sdgm/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/sdgm/_mcp/server.

# Introduction

> Get started with the KumoRFM Fine-Tuning Platform — train and deploy models through the web UI

**The KumoRFM Fine-Tuning Platform** is Kumo's managed web interface for training, evaluating, and deploying graph neural network models on relational data. Connect your data warehouse, define predictive queries, train models, and generate batch predictions — all through the UI without writing code.

For SDK-based workflows, see the [KumoRFM Fine-Tuning SDK](/fine-tuning/introduction) or [KumoRFM SDK](/rfm/introduction) instead.

The platform workflow follows these steps:

Connect to S3, BigQuery, Snowflake, Databricks, or upload local data.

Write predictive queries, configure model settings, and train.

Generate batch predictions and export results.

Manage quotas, security, deployment options, and SSO.