Building Blazing Fast AI-Native Apps: A Developer's Guide to the Database Underneath

AI-native apps put unusual demands on your data layer, vector search alongside structured queries, real-time feature lookups, high-cardinality event streams, and sub-second analytics at a scale most databases were never built for. In this session, we'll walk through how to actually build on ClickHouse as the core database for an AI-native app: handling embeddings and hybrid search, ingesting high-volume application events in real time, and running ad-hoc analytical queries your product and eng teams need without bolting on a second system. As your app matures into agentic workflows, that same database has to absorb a new kind of data — every tool call, retry, and reasoning trace your agents produce. We'll close with a live demo. One database, from your first AI feature to your most complex agent.