Building the Foundations for Trustworthy Agent Automation

The Data, Agents, and Processes Lab (DAPLab) at Columbia University develops the systems, infrastructure, and interaction principles required for AI agents to safely and reliably automate real work.

We believe trustworthy agent automation cannot be solved at a single layer of the stack. DAPLab vertically integrates expertise across operating systems, data systems, AI, HCI, security, and enterprise workflows to build end-to-end agentic systems with real guarantees around reliability, observability, safety, and control.

For more information about the lab, please contact ewu@cs.columbia.edu

Why Vertical Integration Matters

AI agents fail across the entire stack: models hallucinate, retrieval misses critical context, execution environments lack isolation, workflows leak data, and human oversight breaks under scale. Fixing only one layer is not enough.

DAPLab brings together researchers across systems, databases, AI, HCI, security, and organizational workflows because trustworthy automation requires coordinated advances across the full agent stack — from infrastructure and state management to evaluation, safety, and human interaction.

Human Interaction ↑ Agent Reasoning + Learning ↑ Retrieval + Memory ↑ Workflow + Policies ↑ Data + Execution Systems ↑ OS + Infrastructure

Trustworthy Automation Requires Integration Across Layers

News & Education

New Blog Series: Agentic Data Environments

We’re publishing a series of posts on what it takes to build data environments for AI agents. The first post lays out the vision; the second digs into why today’s branchable databases aren’t ready for agentic workloads. More posts coming soon.

Trustworthy AI for Code, Industry Roundtable NYC

A curated, invite-only gathering of industry and academic leaders at the IBM Flagship Office in New York City (June 3, 2026) to discuss trustworthy AI for code. Co-organized by DAPLab (Eugene Wu), Baishakhi Ray (Columbia), Abhik Roychoudhury (NUS), and IBM Research.

DAPLab Receives Microsoft Azure Credit Award

DAPLab has received a $250K Microsoft Azure credit award through the AARI program to support research on robust generalization in agentic AI. The funding enables work on environment scaling and diversification to improve the reliability of agentic systems in real-world deployments.

Spring 2026 DAPLab Research Seminar

The DAPlab’s Tuesday 12PM research seminar in CSB 453 (CS Conference Room) invites speakers that can share cutting-edge agent-systems research or can talk about processes in their organizations and how they are trying to automate them.

Student Honors & Fellowships

Celebrating recent student recognitions: IBM PhD Fellowship (Jerry Jiaxiang Liu), AI & Autonomous Fellowship (Alex Jiakai Xu), and CRA Outstanding Undergraduate Researcher Honorable Mention (Tianle Zhou).

More news...

Events

  • 2026-06-03
    Trustworthy AI for Code, Industry Roundtable NYC Baishakhi Ray, Eugene Wu, Abhik Roychoudhury, Maja Vukovic

    A curated gathering of leaders from industry and academia for a day of invited talks, sharp di...

  • 2026-05-08
    2026 North East AI Agents Day

    The 2026 North East AI Agents Day is a one-day workshop that brings together researchers and p...

  • 2026-05-05
    Agentic Risk Standard Wenyue Hua

    Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adv...

  • 2026-04-30
    Empowering Future Gen-AI Enterprise and Research Through AI-Native Cloud: Together AI's Perspective Leon Song, Together.AI

    We are living in the era of GenAI, which has transformed not only the computing industry but a...

More events...

Publications

More publications...
Thanks to our industry partners