Five months treating bugs like patients and coding agents like a medical team
Cockroach Labs successfully migrated their database tool to support IBM Db2 using an autonomous AI agent system. The project was completed significantly faster and cheaper than previous manual efforts by using agents to decompose tasks and write code.
Why it matters
This case study illustrates the potential for AI agents to handle complex, multi-step engineering tasks, drastically reducing development time and costs.
Between a Wednesday evening and a Friday afternoon in April, MOLT , the tool Cockroach Labs ships for migrating databases to CockroachDB, gained the ability to migrate from IBM Db2 sources.
Db2, one of the first commercially available relational databases, has a rich SQL dialect, a complex type system, and a native wire protocol. Supporting it in MOLT meant a new schema converter, a new Fetch path for pulling rows out and getting them into CockroachDB, a new Verify path for comparing them once they were loaded, a vendored ANTLR grammar, a Docker image for CI, and more than ten thousand lines of test fixtures. When we added Oracle support to the MOLT tools in 2024, the equivalent work took 9 months, and cost around $160K in engineering time.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in