For the complete documentation index, see llms.txt. This page is also available as Markdown.

Builder journey

See how AI activation supports discovery, design, planning, build, and validation of Data Products.

For a builder or owner, AI activation extends beyond consumption. The assistant can guide the user through a structured Data Product lifecycle, from checking what already exists to a deployed product.

Stages

Stage
What the assistant helps with

Discover

Searches the Data Product catalog and table index for existing coverage before any design work starts.

Design

Clarifies the business problem, consumers, and key questions.

Plan

Locks entities, joins, measures, dimensions, grain, and freshness expectations into a reviewed spec.

Build

Generates a project scaffold, applies syntax templates, and reviews generated SQL or YAML before handoff.

Validate

Checks syntax, quality rules, tests, metadata, and assumptions before the Data Product is promoted.

Deploy

Hands the validated project to Git and deployment so it becomes a live, discoverable Data Product.

For the full walkthrough of these stages, see Build journey with AI.

Workflow expectations

The builder workflow is grounded in the approved design spec and retrieved DataOS examples.

The assistant should mark assumptions, surface TODOs, and ask for confirmation at key checkpoints instead of silently filling gaps.

Last updated

Was this helpful?