Building AI-Enabled Gateways for Data Publication, Discovery, and Analysis
- Lee Liming
- Andy Boughton
- Online
Motivated by the growing data sharing and collaboration needs in the research enterprise, we will describe how Globus services may be used to dramatically increase the value of research products. In this tutorial we will demonstrate how to easily generate and deploy a data portal—without hosting infrastructure—and automatically generate and ingest metadata into a search index, enabling data publication that meets FAIRness mandates while ensuring compliance with security and privacy regimes. We will then evolve the portal to a science gateway by adding remote computation via functions-as-a-service (FaaS), making the data reusable by collaborators. Finally, we will introduce the Globus Model Context Protocol (MCP) server and demonstrate how complex remote computation tasks can be delegated to AI agents, allowing the research pipeline to scale without human effort.