Make your data AI agents ready with Fivetran + dbt Labs

Detailed schedule:

17:30 Doors open, welcome drinks

‍

17:45 Welcome to UpToData

Cédric Pompeï, Founder & CEO, Argusa SA

‍

18:00 Fivetran + dbt Labs presentation

Hicham Babahmed, Partner Solutions Architect, Fivetran + dbt Labs

Open by design: building the data foundation AI agents need

Everyone is talking about AI agents. But agents are only as useful as the data they can access, understand, and trust.

In this session, we'll explore why preparing your data for AI starts with building an open data infrastructure. You'll learn how the shared vision of Fivetran and dbt Labs helps organizations create governed, interoperable, AI-ready data foundations instead of locking intelligence inside proprietary platforms.

We'll then show how that vision comes to life in the dbt platform through capabilities like dbt Wizard, an AI agent for governed analytics engineering, and dbt State, which understands what's actually changed to make development and deployments faster and more efficient.

Along the way, we'll also cover the latest announcements from dbt Summit and what they mean for teams building the next generation of data platforms

‍

‍18:45 Education First presentation

Adrien Ledoux, Director of Analytics and Data Platform, Education First

Building a Data Culture at EF Tours, and Learning What Our Data Products Are Worth

At EF Tours, we operate in a deliberately decentralized world; domains own their data, their tools, and their decisions. That autonomy drives innovation, but it also created silos, inconsistent definitions, and a lot of reinvented wheels. This talk is about how we turned that decentralized chaos into a real data culture, and what we learned once that culture matured enough to ask a harder question: what is our data actually worth?

We'll walk through how Fivetran & dbt became the technical and cultural foundation for that shift; first dbt Core as a shared control plane for testing, documentation, and transformation, then dbt Platform as a catalyzer for unified metadata, observability, and cataloging across a decentralized mesh of teams. We'll cover the medallion architecture that let domains keep ownership while still building on a common foundation, and the "you own your domain, we enable your success" model that made adoption stick.

Once that foundation was in place, a new question emerged from the business: not just "is the data trustworthy?" but "what is this data product costing us, and who's actually using it?" We'll show how we answered that with mart_metadata, a dbt-native observability layer that tracks build consumption, Snowflake credit costs, Power BI usage, and downstream query patterns; stitched into a single model of cost and usage per data product. We'll cover the scoring methodology behind it, the cost attribution layer in dbt, the semantic layer in Snowflake, and how a Cortex Agent turned that intelligence into something conversational, so anyone can get a grounded answer without writing a query.

You'll leave with a practical model for building data culture in a decentralized organization, a concrete scoring formula for dbt model performance, a pattern for attributing Snowflake credits to individual data products, and a working example of a Cortex Agent as the interface layer.

‍

19:15 Argusa use case

Data Consultant, Argusa SA

‍

19:45 Q&A, discussion and networking

Exchange with the speakers and other data professionals

‍