That's no longer the default.

Google just shipped the Data Science Agent for BigQuery – available in Colab notebooks, and it's in GA right now.

Here's what it actually does:

  • You describe the business outcome in plain language
  • The agent explores and featurizes the data automatically
  • It builds, trains, and validates the ML model
  • It returns accuracy scores – you review, compare, decide

No scaffolding code. No manual feature engineering. No three sprints before the first prototype.

The data scientist's job doesn't disappear – it moves upstream. Less time on setup, more time on the decisions that actually require human judgment.

Are you already using agent-assisted ML workflows, or still building models the manual way?

Want a stronger data analyst role or a raise? Grab the FREE Product Analyst Playbook and get the exact roadmap to your next offer.