Cyberbullying represents a pervasive and evolving threat within digital environments, exacerbated by the scale, anonymity, and immediacy of online interactions. While recent advances in Artificial Intelligence (AI), particularly in Natural Language Processing (NLP), have significantly improved the ability to automatically detect harmful content, a critical gap persists between detection and effective intervention. Existing approaches primarily focus on identifying cyberbullying instances, but they often lack mechanisms to operationalize prevention guidelines and translate them into consistent, actionable responses. This paper addresses this gap by proposing a novel framework that integrates AI-based cyberbullying detection with Business Process Model and Notation (BPMN) to transform textual prevention guidelines into executable workflows. The framework leverages AI models to analyze user-generated content and identify potential cyberbullying signals, which are then used to trigger BPMN-based processes representing structured intervention strategies. A key contribution of this work lies in the systematic mapping of unstructured policy documents into BPMN constructs, allowing organizations to bridge the gap between high-level guidelines and operational procedures. The proposed approach is illustrated through a detailed modeling of cyberbullying prevention guidelines, demonstrating how complex policies can be translated into actionable pipelines. By combining the strengths of AI-driven detection and process-oriented modeling, this work contributes to the development of more effective and scalable cyberbullying prevention systems. Ultimately, the framework aims to support the creation of safer digital environments by enabling not only the identification of harmful behavior but also the consistent execution of appropriate and timely responses, paving the way for future research at the intersection of AI, process management, and digital safety.