This paper presents the iterative development of Habit Coach, a GPT-based chatbot designed to support users in habit change through personalized interaction. Employing a user-centered design approach, we developed the chatbot using a Retrieval-Augmented Generation (RAG) system, which enables behavior personalization without retraining the underlying language model (GPT-4). The system leverages document retrieval and specialized prompts to tailor interactions, drawing from Cognitive Behavioral Therapy (CBT) and narrative therapy techniques. A key challenge in the development process was the difficulty of translating declarative knowledge into effective interaction behaviors. In the initial phase, the chatbot was provided with declarative knowledge about CBT via reference textbooks and high-level conversational goals. However, this approach resulted in imprecise and inefficient behavior, as the GPT model struggled to convert static information into dynamic and contextually appropriate interactions. This highlighted the limitations of relying solely on declarative knowledge to guide chatbot behavior, particularly in nuanced, therapeutic conversations. Over four iterations, we addressed this issue by gradually transitioning towards procedural knowledge, refining the chatbot's interaction strategies, and improving its overall effectiveness. In the final evaluation, 5 participants engaged with the chatbot over five consecutive days, receiving individualized CBT interventions. The Self-Report Habit Index (SRHI) was used to measure habit strength before and after the intervention, revealing a reduction in habit strength post-intervention. These results underscore the importance of procedural knowledge in driving effective, personalized behavior change support in RAG-based systems.

翻译：本文介绍了基于GPT开发的聊天机器人"习惯教练"的迭代开发过程，该系统旨在通过个性化交互支持用户改变习惯。我们采用以用户为中心的设计方法，利用检索增强生成（RAG）系统开发该聊天机器人，该系统无需重新训练底层语言模型（GPT-4）即可实现行为个性化。该系统通过文档检索和专门设计的提示词来定制交互策略，其理论基础来源于认知行为疗法（CBT）和叙事疗法技术。开发过程中的一个关键挑战在于如何将陈述性知识转化为有效的交互行为。在初始阶段，聊天机器人通过参考教科书和高层次对话目标获得了关于CBT的陈述性知识。然而，这种方法导致了交互行为不精确且效率低下，因为GPT模型难以将静态信息转化为动态且符合语境的交互。这凸显了仅依赖陈述性知识来指导聊天机器人行为的局限性，尤其是在需要细微差别的治疗性对话中。经过四次迭代，我们通过逐步转向程序性知识、优化聊天机器人的交互策略并提升其整体有效性，解决了这一问题。在最终评估中，5名参与者连续五天与聊天机器人进行交互，接受了个体化的CBT干预。研究采用自我报告习惯指数（SRHI）测量干预前后的习惯强度，结果显示干预后习惯强度有所降低。这些结果强调了程序性知识在推动基于RAG的系统提供有效、个性化行为改变支持方面的重要性。