Clark Stevens

Building enterprise AI applications shouldn't require every team to reinvent the wheel — standing up data pipelines, managing security, and keeping knowledge bases current. Blue Origin faced this at scale: dozens of teams, hundreds of data sources, and growing demand for AI apps that could reason across all of it.

At Blue Origin, Databricks is the central data lakehouse for design, manufacturing, and launch operations. Scaling to thousands of pipelines without scaling headcount required rethinking how we manage data in the first place. We will share how we use AI and automation to build pipelines and tables with no human intervention required and how we automated data quality and metadata management to make our data AI ready. This enables federated data teams across the company to use trustworthy data and AI to build a road to space! We will walk through a multi-agent system built on this foundation to manage satellite telemetry. An orchestrator queries a knowledge graph of prior episodes and a vector store of resolution procedures, then routes tasks to specialist agents for anomaly classification, forecasting, resolution, and command safety validation. Each execution is captured, clustered, and distilled back into procedural memory, so the system improves from its own operational history.