NODES AI 2026 - Graph-Powered Storyworlds: Using Neo4j To Keep 1M+ Word LitRPG Epics Coherent w/ AI

In this session, Prem Chandrasekaran discusses how Neo4j serves as the backbone for an AI-assisted platform designed for long-form LitRPG series. He explains the limitations of large language models in maintaining narrative coherence across expansive stories and demonstrates how a narrative knowledge graph is created from raw manuscripts. The talk covers the synchronization of the graph as chapters evolve, the use of Cypher queries for continuity checks and world consistency, and the application of Neo4j as both a long-term memory resource and a safety mechanism in AI content generation. Attendees will gain insights into effective graph modeling patterns for narrative contexts and learn how to utilize Neo4j queries to provide targeted context for LLMs, ensuring that AI-generated content remains coherent over time.