Ram Alagappan (UIUC)
AI agents can monitor live data, investigate anomalies, test hypotheses, and take actions. But today’s streaming systems were built for hand-written programs, not AI agents that are speculative, exploratory, and sometimes wrong. This creates two fundamental problems. First, agentic workloads can interfere with production workloads. Second, letting agents write directly to live streams is risky: a bad decision can result in catastrophic failure of downstream systems. I will argue that the shared log, the core abstraction behind modern streaming systems, should become forkable to support agents acting on live data. A fork gives an agent an isolated instance of a live stream in which it can explore, run what-if analyses, and stage changes without disrupting production. I will present AgileLog, a forkable shared-log abstraction with novel primitives designed for agents operating on live, streaming data. I will then present Bolt, an implementation of AgileLog, and demonstrate how it makes forks very cheap while providing logical and performance isolation.
Ram Alagappan is an Assistant Professor of CS at the University of Illinois Urbana-Champaign, where he co-leads the DASSL systems group. His research spans distributed systems, data streaming, disaggregated memory, and more recently, data infrastructure for AI agents. Ram’s work has won an NSF CAREER Award, a Google ML and Systems Junior Faculty Award, and a NetApp Faculty Fellowship. His papers have received Best Paper Awards at SOSP ’24 and FAST ’20, ’18, and ’17, a Best Student Paper Award at CAIS SAO ’26, and a Best Paper nomination at OSDI ’26. Ideas and protocols from his research have been adopted in a financial database, and a popular data streaming platform. Ram has also been recognized three times for teaching excellence at UIUC.