Jordan Tigani

AI agents can now write good SQL and work through a question over many turns, so self-service analytics may finally be here. Jordan Tigani looks at what that means for data teams: fewer handoffs, and a new role, the Data Intelligence Engineer, who owns the data model, the context, and the answers.

AI agents are now heavy users of data tools, using them to query warehouses, build dashboards and write pipelines. This session shares three shifts we've made at MotherDuck building data infrastructure for this new world. We’ll cover: - Tradeoffs of owning the agent harness vs. the BYO agent model - The role of CLIs, Model Context Protocol and context layers in the data stack - How to create products agents can discover, sign up for, and use We'll also discuss two architectural decisions we made prior to the agent era and why they didn't have to change once agents came knocking.

DuckDB is well-loved by SQL-ophiles to handle their small data workloads. How do you make it scale? What happens when you feed it Big Data? What is this DuckLake thing I've been hearing about? This talk will help answer these questions from real-world experience running a DuckDB service in the cloud.

DuckDB is taking the analytics world by storm. This talk will talk about what makes DuckDB so ducking awesome. We’ll dig into DuckDB use cases, syntax, connectors, architecture, and features that make it more than just another query engine.

Running a full-fledged analytical database inside the client opens up new ways of executing your query; you can run parts of your query locally and part remotely.