How AlphaSense turned a 3-to-5-week data rebuild into a few hours with dbt and Euno's AI context

Sarah Levy, co-founder and CEO of Euno, and Brad Levy, director of analytics at AlphaSense, presented a real-world case study of running AI agents on enterprise data. Their premise: AI demos look clean on stage, but production data is federated, fragmented, and full of conflicting definitions, and succeeding in that messier reality requires context that is automated, governed, and scoped, not assembled by an agent on the fly.

Euno continuously crawls metadata across a company's stack (data platforms, ETL and ELT tools, BI, security, and observability systems) and reconstructs it into a live context graph that captures how data assets relate to each other, not just that they exist. AlphaSense uses dbt as its governance layer on top of that context, and the session walked through three use cases built on the combination.

The first was rebuilding a legacy dashboard model: one 287-field table with 68 dbt models upstream of it, powering 12 dashboards for roughly 300 users, where the real business logic lived in the BI layer instead of dbt. Using Euno for context and Cursor as the IDE, Brad rebuilt it as a governed star schema of 13 models in about 15 prompts across a single session, reconciling the new models against the legacy ones for parity before shipping.

Work that would normally take three to five weeks came down to one focused build-and-validation cycle of a few hours, and roughly half of the resulting diff was tests and documentation rather than net-new logic.

The second use case involved redesigning a billing architecture that had outgrown a single fact table as a second product line arrived. This one generated no code at all: Euno traced the current state to the column level, and the proposed redesign, including two Mermaid diagrams, was delivered as a Notion document for AlphaSense's data architect to review and comment on directly.

The full proposal took about two focused hours with an agent, compared with an estimated day and a half by hand. The third use case, still in progress, is scaling conversational analytics so that many agents across the business pull from the same governed context instead of each one reconciling metadata independently and disagreeing with the others.

AlphaSense summarized the payoff in three points: the resulting models were more accurate because they came out governed and tested, not just generated; the work was faster, measured in hours instead of weeks; and, perhaps unexpectedly, the work was more enjoyable, since time shifted from re-tracing what already existed toward actual judgment and design.

In the Q&A, Levy and Levy discussed how Euno's live labels (encoded rules like "certified if it only queries gold-layer dbt models") turn conflicting definitions, like two different definitions of churn from different teams, into an explainable choice rather than a guess, and how Euno's benchmark-question mechanism continuously checks agent accuracy over time rather than relying on a single point-in-time evaluation.

Watch every keynote and breakout from dbt Summit 2026 on demand. Watch dbt Summit 2026 on demand →