Annotated data remains essential for training and evaluating NLP systems. Large language models have broadened the kinds of data researchers need, including multimodal and agentic system data. Here, we introduce Potato 2.0, a major update to our open source annotation platform designed for easy deployment, customization, and fully reproducible and shareable annotation designs. Potato offers broad support for many types of annotations in NLP, including 39 different types of annotation tasks, support for text, audio, image, and video modalities, or mixtures thereof. Potato 2.0 includes robust support for labeling agentic system outputs through reading common trace formats, or live interaction and annotation with agents in multiple settings, such as chatting, web-browsing, and coding. Potato also includes multiple AI-assistance features to help annotators more easily label data. Finally, Potato introduces a new agentic AI-in-the-loop workflow where a single human annotator collaborates with an LLM through iterative prompt refinement, uncertainty-driven instance selection, and progressive autonomy—enabling efficient dataset creation without a large annotation team.