Join me live with the @claudeai team!
We're discussing self-improvement loops - how to improve agent skills based on feedback overtime. It's the backbone of our agent management process for Warp's open-source repo.
Working on a new way to orchestrate agents.
- Agent makes a delegation plan with subagent tasks
- Run subagents locally, or in Dockerized cloud environments
- Subagents send and receive messages as they work
Run /orchestrate or let the agent use the delegation tool. Wdyt?