Objective: To address the insufficient integration of theory and practice in surgical clinical clerkship teaching, the limited availability of authentic clinical cases, and the limitations of traditional standardized patients (SPs) in terms of consistency and organizational cost, this study aimed to develop an artificial intelligence-based standardized patient (AI-SP) teaching framework grounded in structured clinical case data. Lumbar disc herniation was used as a representative condition for application and exploratory implementation. Methods: An exploratory teaching application design was adopted. Based on the learning objectives of the lumbar disc herniation chapter in standard surgery textbooks, a layered AI-SP system was developed, comprising a case data layer, a clinical rules and teaching logic layer, and an AI interaction layer. Clinical case data were derived from a single-center spine surgery practice and were de-identified and structured into teaching-oriented data units. Diagnostic and therapeutic principles from textbooks, together with expert consensus and clinical guidelines, were abstracted into rule constraints and scenario evolution logic. The interaction layer employed a large language model to support multi-turn dialogue, with standardization ensured through role restriction, rule-based control, and consistency validation. The system was embedded into three stages of clerkship teaching—pre-clerkship preparation, in-clerkship guidance, and post-clerkship consolidation—and representative interaction workflows were developed. Results: A layered AI-SP architecture and information flow model tailored for surgical clinical clerkship teaching was established. Under predefined rule constraints, the system was able to generate stable patient narratives consistent with textbook content and clinical reasoning, enabling reproducible and controllable standardized teaching scenarios. An exploratory application suggested that the AI-SP facilitated the formation of a more structured disease understanding before students entered real clinical settings, improved the consistency and focus of clerkship discussions, and supported repeated practice under conditions of limited clinical resources. Quantitative evaluation of learning outcomes was not conducted in this study. Conclusion: The AI-SP framework, developed using artificial intelligence and structured clinical case data, may serve as an auxiliary tool for surgical clinical clerkship teaching by providing a controlled and standardized interactive training environment without replacing students’ clinical judgment. Future studies should incorporate multicenter case data and employ controlled designs with quantitative outcome measures to systematically evaluate the educational effectiveness.