Building a data context layer to fix your AI analytics

Agents are now consumers of your data stack, and unlike analysts they never pause to ask whether a metric is accurate or still relevant. How do you make your data platform robust? What are the best tools out there for both BI and AI analytics, and are they sufficient to prevent semantic rotting?

This session is about the part most tooling skips: who owns your definitions? who keeps them true as the business changes? Who decides which definition of “active user” is used by Claude?

Thomas will share Tasman’s view – built over seven years and 70 fast-growing clients – on how to set up your data foundations so that there is a proper source of truth in data, semantics, and context. And we will not just show you the slides; we’ll walk through a few real examples.

You’ll leave with clarity on how governance changes in the world of AI, and a practical framework for keeping your semantic and context layers current.