Developed a personalized multimodal input feature for the MSDLLCpapers/teal-agents repository, enabling the system to process both text and image inputs while incorporating user-specific context such as location, preferences, and history. Leveraged Python for backend development and applied full stack and API development skills to integrate user-context data, allowing the application to generate tailored responses and enhance user engagement. Focused on privacy-conscious design and commit traceability, the work established a foundation for future expansion into additional modalities. No major bugs were reported during this period, reflecting a focused and well-scoped implementation of machine learning-driven personalization capabilities.