People working with data often move their data across multiple applications, because they rely on these apps' complementing user experiences to best complete their tasks. Since traditional copy-and-paste approaches do not accommodate diverse table representations adopted by different apps, users spend considerable effort to reconstruct data formats and visual representations, making cross-app workflows costly. For example, when transferring a spreadsheet table with conditional formatting to a markup document, users spend substantial time translating its structure into appropriate tags and manually reformat color. This paper introduces MagicCopy, an AI-powered cross-app copy-and-paste, leveraging source and target contexts and user-specified instructions in natural language to automatically extract, parse, transform, and (re)format data from one app to another. In a study with sixteen participants, users quickly learned and applied MagicCopy to move data across three pairs of tools. Participants further explored diverse applications of MagicCopy to support more streamlined crossed-application interaction in their workflows.

翻译：摘要：处理数据的用户常常在多个应用程序之间迁移数据，因为需要借助这些应用互补的用户体验来高效完成任务。由于传统复制粘贴方法无法适应不同应用采用的不同表格表示形式，用户需花费大量精力重建数据格式与视觉表征，这使得跨应用工作流程成本高昂。例如，当将包含条件格式的电子表格迁移到标记文档时，用户需要耗费大量时间将表格结构转换为相应标签并手动重新编排颜色。本文提出MagicCopy——一种基于人工智能的跨应用复制粘贴工具，利用源端与目标端上下文及用户以自然语言指定的指令，自动完成数据的提取、解析、转换与（重）格式化。在十六名参与者参与的研究中，用户快速掌握并运用MagicCopy在三组工具之间迁移数据。参与者还进一步探索了MagicCopy的多种应用场景，以支持工作流程中更流畅的跨应用交互。