Warp + Docker Fireside chat: Scaling AI Agents Beyond Your Laptop

A conversation between Warp CEO Zach Lloyd and Docker President Mark Cavage on how AI agents are evolving from local tools to autonomous systems, and what that means for engineering workflows. They focus on the infrastructure challenges of running agents at scale, including orchestration, parallelism, and the need for safe execution environments. Oz (by Warp) helps orchestrate cloud agents: deploying agents at scale requires teams to build extensive scaffolding so developers stay in control. Oz makes it easy for teams to embed agents into existing tech stacks, track agents centrally, and continue work locally. Sandboxes (by Docker) help agents execute safely: as agents move from local experiments to autonomous systems, a safe, isolated runtime becomes essential to let them operate freely without risking the host or underlying infrastructure.