Topic
Neo4j
4 episodes
-
Enterprise AI agents fail because they forget
Justy and Cody dig into the claim that enterprise agents don’t mainly fail because models are weak, but because the systems around them don’t preserve applicable, time-scoped decision memory. They unpack the article’s idea of a decision context graph, where it sounds technically solid, and where the startup pitch still feels unproven.
-
Architectural patterns for graph enhanced RAG: Moving beyond vector search in production
Justy and Cody dig into graph-enhanced RAG, where vector search gets structural backbone from graph databases to handle multi-hop reasoning in interconnected enterprise data. They explore the hybrid retrieval pattern, debate whether ingestion-time entity extraction holds up in practice, and question who actually needs this complexity.
-
GraphRAG in Practice: How to Build Cost Efficient, High Recall Retrieval Systems | Towards Data Science
In this episode, we explore GraphRAG, a new methodology for building retrieval systems that blend graph and vector searches to enhance information retrieval efficiency. We discuss its practical implications, explore who benefits from this innovation, and examine concrete examples of usage scenarios.
-
Why LLMs Aren’t a One Size Fits All Solution for Enterprises | Towards Data Science
Large Language Models Why LLMs Aren’t a One-Size-Fits-All Solution for Enterprises What LLMs are (and aren’t) optimized for, and how the industry is approaching AI over structured business datasets — including one approach developed by my team and me. Jure Leskovec Nov 18, 2025 10 min read Share image by author Executives everywhere are racing to use LLMs, but often for tasks they aren’t well-suited to.