Effective study strategies fail when preparatory tasks consume learning time. While AI educational tools demonstrate efficacy, understanding how they align with self-regulation needs in authentic study contexts remains limited. We conducted formative design research using an AI flashcard prototype, employing large language models to generate design hypotheses, which were validated through researcher walkthroughs and student sessions. Six students across disciplines completed sessions combining interviews and think-aloud tasks with their materials. Analysis revealed that students value automation for addressing the overwhelming preparation burden, yet require transparent, editable AI outputs to maintain cognitive ownership, which is essential for self-regulation. They conceptualized AI as a collaborative partner demanding verifiable reasoning rather than an autonomous agent. Metacognitive scaffolding was endorsed when clarifying study direction without constraining choice. Motivational features produced divergent responses. We derive design principles prioritizing editability and transparency, scaffolding metacognition without prescription, and accommodating motivational diversity. Findings identify conditions under which automation supports versus undermines metacognitive development in self-regulated learning.

翻译：当准备性任务消耗学习时间时，有效的学习策略便会失效。尽管AI教育工具已展现出效能，但对其如何在实际学习情境中与自主学习调控需求相契合的理解仍显不足。我们采用基于大语言模型生成设计假设的AI闪卡原型开展形成性设计研究，并通过研究者走查与学生实验环节进行验证。六名跨学科学生完成了结合访谈与有声思维任务的实验环节，过程中使用其自有学习材料。分析表明，学生重视自动化功能以应对繁重的准备负担，但同时需要透明、可编辑的AI输出以保持认知所有权——这对自主学习调控至关重要。学生将AI概念化为需要可验证推理的协作伙伴，而非自主代理。元认知支架在明确学习方向而不限制选择时获得认可。激励性功能则引发分歧性反馈。我们提出以下设计原则：优先考虑可编辑性与透明度，提供非强制性的元认知支架，并适应动机多样性。研究结果明确了自动化在何种条件下支持或阻碍自主学习中元认知能力的发展。