AI can write SQL, generate pipelines, build infrastructure, create database migrations, and even diagnose production problems.
But what happens when it confidently does the wrong thing?
As AI becomes part of how we build and operate modern data platforms, the key question is no longer just, “Can AI generate this?” It’s whether we can trust the result, deploy it safely, observe what happens, and recover when things go wrong.
Join Hamish Watson for a practical session on bringing AI-assisted development into production reality. Drawing on experience across SQL Server, cloud platforms, Databricks, and database DevOps, Hamish will explore how version control, CI/CD, automated testing, drift detection, observability, and governance help keep AI-generated changes safe and recoverable.
The session will include practical examples, lessons learned, and a live demo. And, because live demos rarely go exactly to plan, there may even be a surprise or two.
AI might be able to write your data platform. The more important question is: who’s going to keep it running?