BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CAIL//Events//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-WR-CALNAME:CAIL Events BEGIN:VEVENT UID:2026-09-29-raphael-shu@cail.columbia.edu DTSTAMP:20260929T042550Z DTSTART:20260929T160000Z DTEND:20260929T170000Z SUMMARY:Agents Seminar: Raphael Shu - OpenAgents: The Next-Gen Collaborati on OS for Teams of Humans and Agents LOCATION:CSB 453 DESCRIPTION:AI agents are becoming capable of doing substantial work\, but turning individual capability into effective teamwork remains an open pro blem. The next challenge is not simply how one person uses one agent\, but how teams of humans and agents work together. How should they share conte xt\, divide responsibilities\, reuse expertise\, make decisions\, and rema in accountable for the result? This talk presents the vision behind OpenAg ents: a collaboration OS that gives human teams and agent teams a shared e nvironment for getting work done. People can bring their own agents and pr ivate context\, choose what to share\, and collaborate through persistent threads\, tasks\, and artifacts. Agents can work over long periods\, call specialists\, hand off responsibilities\, and escalate decisions to the ri ght person. Humans set direction\, contribute judgment\, review results\, and remain responsible for the outcome. We will examine concrete scenarios \, including a software change moving through agent review\, human approva l\, deployment\, and testing\, and a specialist agent whose expertise beco mes reusable by colleagues and their agents. These examples reveal the inf rastructure mixed teams need: shared context\, clear ownership\, reliable handoffs\, permissions\, and continuity across people\, agents\, and runti mes. The talk then considers how open collaboration interfaces could exten d this model beyond a single application and support a broader ecosystem o f human-agent teamwork.\n\nhttps://cail.columbia.edu/events/2026-09-29-rap hael-shu URL:https://cail.columbia.edu/events/2026-09-29-raphael-shu END:VEVENT END:VCALENDAR