New! Relate by Neo4j | An embedded database for AI agents Learn More

NODES 26 — November 12, 2026

GraphRAG for Good: Context-Aware AI for Women’s Safety and Financial Freedom

Session track: Data Intelligence

Session time:

Session description:

What does it take to build an AI system that truly understands the complex, interconnected realities of the people it is meant to help? When supporting women escaping domestic abuse, standard AI responses fall short—context, safety, and nuanced relational understanding are critical to guiding survivors toward long-term financial independence. In this session, explore how the non-profit Creating Wings is leveraging Neo4j and GraphRAG (Graph Retrieval-Augmented Generation) to build a deeply context-aware conversational AI agent. Moving beyond basic query-answering, this system connects multi-dimensional data—from immediate safety planning to sustainable career and financial pathways—into a unified knowledge graph that models real-world human needs. Part real-world case study and part technical deep dive, this talk highlights how combining graph databases with generative AI enables technology with true purpose. Attendees will learn practical architectural patterns for context-aware AI and discover how thoughtful engineering can create tangible pathways to safety, opportunity, and freedom.

Speaker

photo of Samay U. Shetty

Samay U. Shetty

AI Researcher

Samay U. Shetty is an AI/ML researcher and engineer specializing in Natural Language Processing (NLP), Large Language Models (LLMs), and Generative AI. He currently works as an Artificial Intelligence Researcher at The Haskell Company, where he designs and develops custom AI solutions to address complex engineering and architectural challenges. He holds a Bachelor’s degree in Electronics and Telecommunication Engineering from the University of Mumbai and is completing a Master of Science in Computer Science at the Rochester Institute of Technology (RIT). Samay also volunteers for the non-profit Creating Wings Co and is a Bernard Kozel Startup Accelerator Fellow at RIT. Across his non-profit and startup work, he builds intelligent systems powered by hybrid neuro-symbolic architectures and Graph RAG pipelines. His research contributions span advanced NLP distributional models, including DisCo-LPI and DiADEM, as well as data processing through MATSAR and PolSARHub.