skinny.

Latest / The CTO Podcast with Fexingo: Technical Leadership, Architecture, and Engineering Org

How Palantir Rebuilt Its Gotham Platform for AI-Native Decision Making

In this episode, Lucas and Luna dive into the architecture behind Palantir's Gotham platform, focusing on its recent overhaul to integrate large language models and real-time data pipelines. They explore how Palantir rebuilt its ontology layer to support AI-native decision making, handling over 10 million daily queries for defense and commercial clients. The discussion covers the shift from batch to streaming data, the embedding of LLMs into core workflows, and the engineering trade-offs between latency and accuracy. Specific numbers include a 40% reduction in decision latency and a 3x…

Log in to save or queue this episode.

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.