The motivation behind this project was to increase transparency in subsidies and make them more accessible to businesses and individuals who may not be familiar with the subsidy landscape. The goal was to simplify the process of discovering and understanding relevant funding opportunities. I began by building crawlers for the largest subsidy platforms in Germany. The scraped data was then pre-processed with Gemini to extract key features such as eligibility criteria, subsidy amounts, and the application process. Next, I developed an agentic Retrieval-Augmented Generation (RAG) system with both keyword search and vector search capabilities. For each user query, hundreds of AI agents are deployed to act as subsidy advisors, searching and matching the most relevant subsidies. The retrieved results are post-processed to ensure they are tailored and directly relevant to the user’s request. To make the system accessible, I built a frontend that allows users to interact with the tool in an intuitive way. Finally, I integrated the Subsidy Finder into Casanoova, my real estate platform, to provide users with an additional layer of financial insights.