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. We work closely with industry partners to ground this research in real organizational needs and ensure it delivers practical impact.

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

MortarBench featured in Realtor.com

Realtor.com covered our MortarBench research on AI mortgage origination agents. Top models got nearly 1 in 4 answers wrong under realistic conditions — and showed systematic bias, flagging non-English names as “foreign origin” at 5× the rate of English names. Matthew Toles and Zhou Yu are quoted in the piece.

Haonan Wang receives inaugural Workday AI PhD Fellowship

Haonan Wang has been awarded the inaugural Workday AI PhD Fellowship to pursue his work on Data Lake Agents. The core question: how do you teach an enterprise agent to gather sufficient, traceable evidence from an organization’s heterogeneous data sources and correctly execute the resulting workflow — while satisfying regulatory requirements, organizational policies, role-based permissions, approval hierarchies, fairness constraints, and operational budgets?

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

  • 2026-08-04
    Summer Agents Research Seminar Henry Yuen, Shuze Chen, Tianyi Peng

    Summer Agents Research Seminar

  • 2026-07-28
    Summer Agents Research Seminar Micah Goldblum

    Topic: LLM and Agent Memory

  • 2026-07-21
    Summer Agents Research Seminar Daniel Hsu

    Topic: Theory of LLMs

  • 2026-07-14
    Summer Agents Research Seminar Carl Vondrick

    Topic: Do multimodal models imagine electric sheep?

More events...

Publications

More publications...
Thanks to our industry partners