2025-11-08 –, Room 301B
Keynote by Chang She
“I’ve seen it, Mr. Anderson. I’ve seen it. The end of all things. I’ve seen the future, and all I see is me”. AI agents are everywhere but the key to their success still lies in data. The more successful we are at connecting our data to agents the better they will become. Agents doing the search are very different from humans doing the search; and unfortunately the world isn’t ready for agents to be doing the retrieval. Systems that support agentic search will need to support bigger scale, more variety of data, and more complex query types. In this talk, let’s explore just what is agentic retrieval, how it’s different from “vanilla” RAG, and what that means for the python data ecosystem.
Chang She is CEO/Co-founder at LanceDB building modern data infrastructure for AI. Previously he architected the ML and experimentation stack at TubiTV as VP of Engineering. In the mythical pre-pandemic epoch, Chang was the 2nd major contributor to Pandas, CTO/Co-founder of DataPad, and a recovering financial quant.