Devin for Databricks Migrations: Less time migrating, more time building
Devin launched Devin for Databricks Migrations, built with Databricks to move enterprises off legacy data platforms and onto Databricks. It's available now on the Databricks Marketplace.
On a migration, Devin converts code from the legacy data warehouse, tests it in the customer's Databricks workspace, fixes what fails, and reconciles every source against its Databricks copy before cutover. The reconciliation checks cover schema, row counts, aggregates, and a row-by-row diff. The source list includes Teradata, Oracle, SQL Server, Informatica, Redshift, and Snowflake, with Databricks SQL, PySpark, Spark Declarative Pipelines, and Unity Catalog on the target side.
Devin can run hundreds of tasks in parallel. Cognition says that's how a Fortune 500 energy company moved a 142-object platform to Unity Catalog in eight days. Zeb, a digital transformation company, used it to build NetSuite-to-Databricks pipelines and 20 tables for an investment advisory firm, finishing a four-week project in two and a half weeks. Those are the vendors' and partner's own figures.
Customers can apply the purchase toward their existing Databricks Universal Commit. Migrations can be run through your Databricks account team with your own engineers, with Databricks field engineers, or with delivery partners such as Zeb.
AI software engineering agent for building features, fixing bugs, reviewing code, and handling work across repositories.