Human collaboration benefits from continuous coordination -- planning, delegating tasks, sharing progress, and adjusting objectives -- to align on shared goals. However, agentic AI systems often limit users to previewing or reviewing an agent's plans for fully autonomous execution. While this may be useful for confirmation and correction, it does not support deeper collaboration between humans and AI agents. We present Cocoa, a system that introduces a novel design pattern -- interactive plans -- for collaborating with an AI agent on complex, multi-step tasks. Informed by a formative study (), Cocoa builds on interaction designs from computational notebooks and document editors to support flexible delegation of agency through Co-planning and Co-execution, where users collaboratively compose and execute plans with an Agent. Using scientific research as a sample domain, our lab (n=16) and field deployment (n=7) studies found that Cocoa improved agent steerability without sacrificing ease-of-use compared to a strong chat baseline. Additionally, researchers valued Cocoa for real-world projects and saw the interleaving of co-planning and co-execution as an effective novel paradigm for human-AI collaboration.
View on arXiv@article{feng2025_2412.10999,
title={ Cocoa: Co-Planning and Co-Execution with AI Agents },
author={ K. J. Kevin Feng and Kevin Pu and Matt Latzke and Tal August and Pao Siangliulue and Jonathan Bragg and Daniel S. Weld and Amy X. Zhang and Joseph Chee Chang },
journal={arXiv preprint arXiv:2412.10999},
year={ 2025 }
}