February 23, 2026 — Leads & Copy —
Snowflake (NYSE: SNOW) announced that Cortex Code CLI, Snowflake’s AI coding agent for local development environments, is expanding beyond Snowflake-native workflows to support any data source across systems, starting with dbt and Apache Airflow.
With this extended support, developers can now use secure, context-aware AI assistance within their preferred data engineering systems. This will allow teams to work with data wherever it resides, and build, manage, and optimize production-grade workflows more efficiently.
The new updates to Cortex Code CLI now support dbt and Apache Airflow workflows.
According to Snowflake, modern data stacks span multiple systems, making data engineering workflows increasingly complex and resource-intensive. When pipelines break, hidden costs can compound, leading to lost productivity, operational friction, and eroded data confidence – ultimately slowing the path to business value. By expanding support to dbt and Apache Airflow workflows, Cortex Code CLI aims to help teams simplify and accelerate development directly within the tools they already use, while maintaining enterprise-grade controls and oversight.
Christian Kleinerman, EVP of Product, Snowflake, said that developers don’t operate in a single system, and AI coding assistants shouldn’t either. He added that modern data work spans multiple systems, teams, and workflows, and the tools Snowflake builds have to reflect that reality. He also stated that by extending Cortex Code CLI beyond Snowflake, the company is advancing its mission to provide developers with a context-aware agent that understands and works across their entire data ecosystem, and by making adoption seamless, Snowflake is meeting developers where they are on their AI journey.
Spencer Burke, SVP of Growth, Braze, said that Cortex Code is transforming how Braze approaches agentic analytics. He added that its native understanding of their datasets, schemas, and columns means their engineers spend less time wrestling with context and more time getting precise, actionable outputs. He also stated that they’re deploying it against more complex data integrations and using it to automate and enrich their insights layer, turning structured analytics into something more dynamic, expressive, and powerful.
Since launching Cortex Code in November 2025, Snowflake reports it has already seen strong adoption with over 4,400 new users. According to Snowflake, teams are rapidly embracing Cortex Code to move faster with greater confidence, turning complex, multi-system workflows into enterprise-ready outcomes.
With the new release, developers unlock:
- Support for dbt and Apache Airflow workflows: Assisting with model development, debugging, and optimization across data transformation and workflow tools
- Expanded AI model choice: Enabling customers to select leading models, including Claude Opus 4.6 and OpenAI GPT-5.2, to balance quality, latency, and cost based on workload requirements, with continued support for the latest frontier models as they become available
- New administrative controls and governance: Providing enterprise features to manage access, usage, and policy enforcement across teams
Trent Foley, Chief Technology Officer, evolv Consulting, said that Cortex Code has transformed solution development at evolv Consulting by providing a direct, context-aware connection to the Snowflake ecosystem, allowing their team to interact seamlessly with databases, objects, and git repositories. He added that by leveraging the most advanced models available, such as Opus 4.6, Cortex Code can essentially ‘do anything’ through its CLI version, from full-featured React app development to complex data engineering tasks. He also stated that this translated into over 500 hours in time saving – roughly $100,000 in value – in just the first 20 days of adoption.
To make Cortex Code CLI accessible to any developer, Snowflake is introducing a new subscription plan that operates independently of Snowflake compute and consumption – which is intended to lower the barrier to entry for any developer team. Snowflake says this marks their first standalone subscription model, offering a self-service path for developers to begin using Cortex Code CLI, without requiring an existing Snowflake deployment, enabling teams to experiment, iterate, and apply AI-powered development across their data workflows.
Source: Snowflake
