Abhinav Anand@abhinav_anand789

FinShield AI is an AI-powered insurance policy intelligence platform that simplifies the understanding and analysis of complex insurance documents. Insurance policies are often lengthy, filled with legal jargon, and difficult to compare, making it challenging for customers and advisors to identify key coverage details, exclusions, waiting periods, and claim conditions. FinShield AI addresses this challenge using a Multi-Agent AI architecture combined with Retrieval-Augmented Generation (RAG). Users can upload insurance policy PDFs, and the system extracts and processes the content, generates semantic embeddings using the all-MiniLM-L6-v2 model, and stores them in ChromaDB for efficient similarity-based retrieval. A Router Agent intelligently directs user queries to specialized AI agents responsible for executive summaries, policy question answering, risk analysis, clause explanation, and policy comparison. By grounding every response in the uploaded policy documents, FinShield AI significantly reduces hallucinations while providing fast, accurate, and context-aware insights powered by Groq's Llama 3 large language model. Built with Python, Streamlit, LangChain, ChromaDB, PyPDF, Sentence Transformers, and Groq, the platform offers an intuitive interface that enables users to understand policies in seconds instead of hours. Its modular architecture is designed for scalability and can be extended with OCR support for scanned documents, multilingual capabilities, cloud deployment, authentication, recommendation systems, and claim eligibility prediction. FinShield AI empowers customers to make informed insurance decisions, helps advisors improve productivity, and enables insurance providers to reduce support costs while delivering a faster, more transparent customer experience.

🌎 Online Hackathon | 📅 August 3–10, 2026| 💻 Powered by native.builder The official native.builder hackathon, hosted by NativelyAI and lablab.ai. Join founders, developers, designers, and builders to create real AI-native applications powered by native.builder: from idea to deployed product, fully in the cloud. 💻 This hackathon is fully online. No travel required.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.