An AlphaSense case study: scaling AI on enterprise data with dbt-first governance and context from Euno
AlphaSense paired dbt's governance with Euno's AI context platform to rebuild legacy models, redesign billing architecture, and scale conversational analytics across the business.
Overview
AlphaSense's early agent efforts hit hallucinations and governance gaps. Shows integrating dbt with Euno's governance tools for unified lineage, ownership, and semantic context across Snowflake, Fivetran, and Tableau, then feeding that trusted context into AI agents including Claude and Cursor.
What you'll take away
- 01
Production data is federated, fragmented, and full of conflicting definitions, so AlphaSense and Euno built context that's automated, governed, and scoped, not assembled by an agent on the fly.
- 02
Rebuilding a legacy dashboard, 287 fields and 68 upstream models, into a governed 13-model star schema took about 15 prompts in a single session, compressing three to five weeks of work into a few hours.
- 03
A full billing-architecture redesign, delivered as a reviewable Notion document with diagrams, took about two focused hours with an agent versus an estimated day and a half by hand.
Session speakers
Sarah Levy
EunoBrad Levy
AlphaSense