Date: September 24, 2026
Time: 11:45 a.m. - 12:45 p.m.
Location: G01 Gates Hall
Title: Early Thoughts on Agentic Data Environments
Speaker: Eugene Wu, Columbia University
Abstract: Autonomous agents promise substantial benefits through speed, scale, and labor savings, but their failures can impose abrupt and irreversible costs. The central challenge for agentic automation is therefore to increase the benefits of automation while bounding the consequences of failure. While databases remain central to modern computing, agents operate across a broader data environment spanning files, APIs, applications, and system state. I will outline some very early work towards Agentic Data Environments — the environment that agents run within — that serve to increase the benefits of automation while bounding their risks. We see data systems as shifting from passive stores of state to active execution substrates that provide safety.
This work is part of the Data, Agents, and Processes Lab (DAPLab) at Columbia, a group of faculty across the technology stack, from HCI, AI, to Data and Classic Systems. More info can be found at dap.cs.columbia.edu.
Bio: Eugene Wu is an associate professor of computer science at Columbia University and Co-director of the new Data, Agents, and Processes Lab (DAPLab). He is broadly interested in the foundations of computing infrastructure that are needed in a future where AI agents can safely, reliably, and efficiently automate complex work. His research spans the computing stack, from visualization and HCI to core data systems. Eugene has received the VLDB 2018 10-year test of time award, best-of-conference citations at ICDE and VLDB, the NSF CAREER, and Google, Adobe, and Amazon faculty awards.
