Snowflake has extended support for Cortex Code CLI, its terminal-based AI coding agent, to dbt and Apache Airflow to help data practitioners streamline engineering workflows.
“With this extended support, developers unlock secure, context-aware AI assistance within their preferred data engineering systems — empowering teams to work with data wherever it lives, and build, manage, and optimize production-grade workflows more efficiently,” the company said in a statement.
Apache Airflow and dbt are widely used building blocks of enterprise data stacks. While dbt provides a SQL-based framework for transforming raw warehouse data into analytics-ready models with testing and version control, Airflow orchestrates and schedules complex data pipelines across systems.
Avoiding context switching for developers
The development could be a big boon for data practitioners and developers.
“These (dbt and Airflow) are the control planes of modern data stacks. Embedding AI assistance directly into transformation and orchestration layers reduces friction, speeds development, and improves governance,” said Phil Fersht, CEO of HFS Research.
Explaining further how Cortex Code CLI’s integration reduces friction and accelerates development, HyperFRAME Research’s leader of the AI stack, Stephanie Walter, pointed out that developers can now avoid context switching.
Before the integration, developers could access Cortex Code CLI through tools like VS Code and Cursor, but the AI-assistance remained “essentially Snowflake‑centric”, offering little awareness of how dbt models or Airflow DAGs were structured, Walter said.
This meant that developers and data practitioners had to generate code in one environment, copy it over to dbt or Airflow, and then manually rework it to fit the transformation or orchestration logic they were maintaining, Walter noted, adding that this was an inefficient, fragmented workflow that kept AI assistance disconnected from real production pipelines.
Snowflake to own the developer experience
The integration could be seen as a strategic move by Snowflake to own the developer experience around data workflows and not just the warehouse.
“Snowflake wants to be the intelligence layer across the modern data stack, even when components sit outside its core platform. The endgame is platform gravity. If developers rely on Cortex to build and maintain pipelines, Snowflake increases its strategic control over data logic, governance, and AI enablement, regardless of where raw data physically resides,” Fersht said.
As a result, Fersht added, the move should intensify competition around the AI-native data stack: “Databricks has long positioned itself around openness and lakehouse flexibility. Snowflake moving Cortex Code CLI into dbt and Airflow narrows that differentiation by signaling it can operate across heterogeneous environments.”
Snowflake has also introduced a subscription plan for Cortex Code CLI to allow customers who don’t already have a Snowflake workload to try the AI coding agent across their data workflows.
Details of the subscription plan are yet to be disclosed by the cloud data warehouse provider.
Go to Source
Author:
