How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

Summary

Ever wondered how NASA identifies its top experts, forms high-performing teams, and plans for the skills of tomorrow? The answer lies in their People Graph! It is an initiative that’s transforming people analytics in NASA with the power of graph databases and large language models (LLMs). Missed the community cal? Watch the full NASA x Memgraph community call on demand to dive deeper into their architecture, live demo, and expert Q&A. Introduction This community call was led by members of NASA’s People Analytics team who are behind the development of the People Knowledge Graph: David Meza, Branch Chief of People Analytics and Head of Analytics for Human Capital at NASA Madison Ostermann, Data Scientist and Data Engineer Katherine Knott, Data Scientist They shared how they combined graph databases, large language models (LLMs), and secure AWS infrastructure to connect people, projects, and skills across the agency. The result is a graph-powered system that enables subject matter experts discovery, project similarity analysis, and generation of real-time organizational insights, all accessible via Cypher queries and a chatbot interface powered by GraphRAG. Here’s a breakdown of the key technical takeaways and live demo shared during the session: Talking Point 1: Why NASA Needed a People Knowledge Graph People data in traditional relational databases is messy. Rows, columns, joins. It’s just not built for the complex relationships that exist in a massive organizations like NASA. Graph databases flip that. Instead of flattening data into spreadsheets, they connect people to skills, projects, and even their career paths, allowing you to answer questions like: “Who has worked on highly similar AI projects across NASA centers?” “Which employees have cross-disciplinary expertise in AI/ML?” “Where are the skill gaps we need to fill?” NASA uses Memgraph to handle all of this in real time, allowing their team to query and traverse multi-hop relationships seamlessly. Talking Po...