Snowflake Unveils Cortex Code AI Coding Agent for Enterprise Data

Snowflake has officially launched Cortex Code, a Snowflake-native AI coding agent designed to accelerate enterprise data development by embedding AI directly into the data engineering workflow with deep contextual awareness of users' specific data environments.

According to Snowflake's press release, Cortex Code "turns complex data engineering, analytics, machine learning, and agent-building tasks into simple, informed interactions with high accuracy—all in natural language," enabling teams to "slash production time" while "empowering every user" to build confidently with data. The agent provides "deep awareness of Snowflake's data and semantics," allowing it to "quickly debug and refactor code with intelligent suggestions tailored to your specific Snowflake environment, tables and views" and perform "complex admin tasks, such as managing catalogs, setting permissions, creating users and optimizing costs" through natural language commands.

Unlike generic AI coding assistants, Cortex Code operates within Snowflake's governed environment, leveraging "a deep understanding of your specific data catalog to simplify discovery and management using natural language." This contextual awareness allows it to generate "fully executable ML pipelines autonomously, ready to run directly in Snowflake Notebooks" while maintaining enterprise security controls. The agent supports integration with popular tools through Model Context Protocol (MCP) and can optimize for quality, latency, and cost using models like Claude Opus 4.6, Claude Sonnet 4.5, and GPT 5.2.

Early adopters report dramatic productivity gains: Snowflake's press release cites TS Imagine stating their engineers now "submitting 5x more PRs, and work that took 3-4 days now takes 2-3 hours." Christian Kleinerman, EVP of Product at Snowflake, emphasized that Cortex Code "reimagines how teams build and operate by embedding AI directly into the development lifecycle with critical data context and controls teams can trust," noting it "materially shifts how organizations build with data and AI, drastically reducing the effort required for users to build solutions that are reliable, governed, and ready to run at enterprise scale."

Cortex Code is now generally available in Snowsight, with a CLI that supports Windows natively, and introduces "Agent Teams" that allow users to "break large projects into parallel work streams—spin up specialized agents for research, coding, and testing that coordinate automatically." This represents a strategic shift from AI tools that merely generate code to ones that understand and operate within the enterprise data context, positioning Snowflake as the "control plane for the agentic enterprise" according to Baris Gultekin, VP of AI at Snowflake.

Enterprise customers including Braze, Decile, dentsu, LendingTree, United Rentals, and WHOOP are already using Cortex Code to accelerate data pipeline development, analytics, and AI application building. The agent joins Snowflake Intelligence as part of Snowflake's broader Cortex AI product suite, extending the company's AI-powered capabilities across the entire enterprise data lifecycle from exploration to production.

For data teams, Cortex Code fundamentally changes the development paradigm by eliminating the context-switching between data exploration and code implementation. As Snowflake positions it, "the future of development on data isn't just better models—it's AI that understands your data context from the ground up." This represents a significant evolution from traditional AI copilots that lack deep integration with enterprise data systems and governance structures.

Snowflake's official Cortex Code product page details the technical implementation, while the press release provides the official launch announcement and customer testimonials.

Artūras Malašauskas is an AI Systems Integrator with 20+ years of production-grade web engineering experience. He has designed, shipped, and scaled enterprise Python/PHP systems for logistics, SaaS, and public-sector clients. For the past year, he has focused exclusively on AI integrations: deploying open-source LLMs, building generative media pipelines (image, audio, video), and engineering multi-agent workflows for real production environments. His standard: reproducibility, security, cost-efficient inference—no vaporware. He documents and evaluates emerging AI tooling, separating verified capabilities from marketing noise. Technical editor at: muza-ai.eu, ai-verslas.lt, ai-naujinos.lt Connect on LinkedIn