Explore the development of an in-house threat modeling assistant that leverages Large Language Models through AWS Bedrock and Anthropic Claude in this 41-minute conference talk from HackMiami XII 2025. Learn how to build a private solution that automates and streamlines the threat modeling process while keeping sensitive security data within organizational control. Discover how this proof-of-concept tool combines LangChain and Streamlit to create an interactive threat modeling experience, and see how modern AI technologies can enhance security analysis while maintaining data privacy. Gain insights from Principal Security Engineer Murat Zhumagali on implementing AI-powered security tools that balance automation with security requirements.