Snowflake launches CoCo AI coding agent and Datastream to reduce developer context switching
By
Chris J. Preimesberger
A five-star bake. Worth schmearing, sharing, saving.
Summary
Snowflake announced new AI-powered developer capabilities at its 2026 Summit, including CoCo (a model-agnostic AI coding agent, formerly Cortex Code) and Datastream. The company argues that developers are slowed down by context switching across multiple tools, and advocates for a governed, AI-powered platform built on a trusted data foundation to streamline enterprise development. The new tools aim to bring governed enterprise development to desktop and Slack environments, reducing friction and enabling the "agentic enterprise."
Key quotes
· 3 pulledSnowflake, fresh off reworking its Cortex Code as Snowflake CoCo, is firing a fastball to developers, urging them to stop being slowed by context switching across tools and start building on a trusted data foundation.
Ready or not, the agentic enterprise is here, and the key to enabling it efficiently is being debated from various perspectives.
Strategies can range from DIY schemes to best-of-breed point solutions to a single, governed, AI-powered tool that manages it all with minimal human oversight.
You might also wanna read
The Evolution of Programming Tools: From Compilers to AI Coding Assistants
The article explores the evolution of programming tools from Grace Hopper's early compilers to modern AI coding assistants, examining how th
wreflection.com·6mo ago
Snowflake signs $6 billion five-year AI chip deal with Amazon Web Services
Snowflake has signed a $6 billion, five-year agreement with Amazon Web Services (AWS) to secure AI CPU chips. The deal is nearly as large as
techcrunch.com·10d ago
AI Coding Tools Struggle with Complex Production Codebases: A Context Engineering Analysis
This article discusses the challenges AI coding tools face when working with large, complex production codebases. It references a Stanford s
github.com·8mo ago
Building a Custom Minimal Coding Agent: Lessons from Three Years of LLM-Assisted Development
The article details the author's three-year journey using various LLM-powered coding assistants, from early ChatGPT usage to modern coding a
Research-Driven Coding Agents Improve llama.cpp Performance with Literature Search Phase
The article discusses how coding agents that incorporate a research phase—reading academic papers and studying competing projects—before wri
blog.skypilot.co·1mo ago
How AI Coding Models Are Outpacing Our Context Control Systems
The author reflects on how their coding process has evolved over the past year while using AI models to write code. They note that while mod