dbt for Cortex AI: A Design Pattern The views and opinions shared in this blog are solely my own and do not necessarily reflect the views of my employer. Preface Snowflake has always continuously …

Snowflake Community is a platform for users of the Snowflake cloud data platform to share knowledge, ask questions, and collaborate. Readers can learn about cloud data warehousing, data analytics, and data engineering best practices. With forums, user groups, and community events, Snowflake Community provides resources for Snowflake users to connect and learn from each other.

Snowflake Community

A design pattern called 'PowerOf2' (PO2) is presented for using dbt as the core deployment engine for Snowflake Cortex AI services — specifically Cortex Agents, Cortex Search, and Semantic Views. The pattern leverages dbt models (with a new 'semantic_view' materialization) and dbt macros to manage AI service creation and modification alongside data objects in a single project. Key advantages include decoupling agent specs from DDL, parameterized deployments, Create-vs-Alter branching logic via Jinja, version control of all assets in one place, and reduced CI/CD complexity. The pattern is positioned as a third alternative to direct SQL scripts or REST API approaches, with concrete code examples and links to a reference GitHub repo.

dbt for Cortex AI: A Design Pattern

Get Chinmayee Lakkad’s stories in your inbox