CoCo

Snowflake CoCo is a data-native AI coding agent that turns complex data engineering, analytics, machine learning, and AI workflows into simple conversations. It understands enterprise context, including catalog, lineage, RBAC policies, compute, and pipeline dependencies, helping generated code reference real objects with the correct permissions. Teams can use CoCo to identify data, build pipelines across dbt, Apache Airflow, Postgres, Spark, and AWS Glue, generate executable ML pipelines for Snowflake Notebooks, and create apps and AI agents grounded in enterprise data. Its agent harness includes Snowflake-specialized tools such as semantic catalog search, data diffing, and sandboxed runtimes rather than relying on generic code wrappers. For complex, multi-step tasks, orchestration can coordinate sub-agents and route between models automatically. CoCo is available as a desktop development environment with access to local files, terminals, and Snowflake.

Coco Alemana is a faster way to work with data. It provides data scientists, analysts and engineers the ability to visually interact with their data to clean, manipulate and analyze datasets of any size. It's a code-optional platform, with extensive connections to remote data sources. It's optimized for getting fast insights, at any data size. For more advanced users, they can continue using SQL to extend the capabilities of Coco Alemana's visual-first interface. Users can expect to save 30 minutes, to 2 hours per day on tedious data cleaning and manipulation tasks. Coco Alemana can be installed in less than 2 minutes, with no prior knowledge of programming, and no data transfers required. Users can connect their credentials and get access to their remote data stores in seconds. It's also heavily integrated into the operating system, allowing for a high performance, cohesive experience.