Everyone aspires to achieve personal goals. However, getting started is often complex and daunting, especially for large projects. AI has the potential to create plans and help jumpstart progress, but it often lacks sufficient personal context to be useful. We introduce JumpStarter, a system that uses AI-powered context curation to create action plans and draft personalized working solutions. JumpStarter assists users by posing questions to elicit relevant context, breaking down goals into manageable steps, and selecting appropriate context to draft working solutions for each step. A technical evaluation indicates that context curation results in plans and working solutions of higher quality. A user study demonstrates that compared to ChatGPT, JumpStarter significantly reduces users' mental load and increases their efficiency in kickstarting personal projects. We discuss the design implications of AI-powered context curation to facilitate the use of generative AI in complex problem-solving.

翻译：每个人都渴望实现个人目标。然而，启动过程往往复杂且令人却步，尤其对于大型项目而言。人工智能具备制定计划并助力项目启动的潜力，但通常因缺乏足够的个人上下文信息而难以发挥实际效用。本文提出JumpStarter系统，该系统通过AI驱动的上下文策展来创建行动计划并草拟个性化解决方案。JumpStarter通过提出引导性问题获取相关上下文、将目标分解为可执行的步骤、并筛选适当上下文为每个步骤草拟实施方案来协助用户。技术评估表明，上下文策展能生成更高质量的计划与解决方案。用户研究表明，相较于ChatGPT，JumpStarter显著降低了用户认知负荷，并提升了个人项目启动效率。本文进一步探讨了AI驱动上下文策展的设计启示，以促进生成式AI在复杂问题解决中的应用。