How Warp builds self improving agents on Claude

Most teams deploy an agent, watch it work, and move on. Warp built something different: agents that study how your team corrects them and rewrite their own skills to do better next time.

Join Warp founder Zach Lloyd and Anthropic Applied AI for a technical look at self-improvement loops: how to capture human feedback signals, turn them into skill updates, and expand agents from one-off helpers into systems that compound across your org. Live demos include Warp’s PR review agent and the social listening bot they use to bring agentic workflows into community management.