Transformation
Transformation3 min readBy The Data Workers Team

Move from a catalog people update to a catalog agents keep current

Traditional catalogs are populated once and go stale. Data Workers moves your glossary, owners and policies into Spellbook, where agents keep definitions, lineage and ownership current as they work.

Before and after

TodayWith Data Workers
A catalog updated by handA catalog agents keep current
Stewards chasing owners in spreadsheetsOwners proposed from usage history
Lineage that is weeks oldLineage that updates with every change
Policy written down, not enforcedPolicy enforced by agents, every grant logged

How it works

1. Import what you have

Glossary terms, owners and policies are imported from your existing catalog.

2. Let agents keep it true

Data Context & Catalog updates lineage and documentation as pipelines change; Access & Governance enforces policy.

3. Govern from Spellbook

Stewards approve, audit and roll back in one place.

The agents behind the data catalog modernization: Data Context & Catalog agent → Data Context & Catalog agent → Data Access & Governance agent → Spellbook Data Catalog.
Fig. 1:The agents behind the data catalog modernization: Data Context & Catalog agent → Data Context & Catalog agent → Data Access & Governance agent → Spellbook Data Catalog.

The impact metrics we move

  • •Catalog freshness: from about a month to under 1 h
  • •Owner assigned: from about 2 weeks to ~1 h
  • •Policy grant: from about a week to 5 min
Time to complete, current practice (black) vs. with Data Workers (green). Illustrative.
Fig. 2:Time to complete, current practice (black) vs. with Data Workers (green). Illustrative.

Where teams start

  • •Collibra and Alation modernization. Keep them or move off; agents keep the content current.
  • •Unity Catalog and Purview enrichment. Agents write definitions and lineage back.
  • •Glossary to governed definitions. Terms become definitions agents answer from.
  • •Stewardship at scale. Owners proposed, not chased.
  • •Policy as enforcement. Rules applied on every request.

The climb: from assisted to autonomous to agentic

Every transformation runs on the same ladder from our thesis: agents first inventory and propose with receipts, then move work in approved waves, and the finished platform keeps running itself once the move is done.

The pilot

  • •Scope. Import one domain's glossary and keep it current for 30 days.
  • •First week. Agents run at L1, observing only, and show the fixes they would have made, with receipts.
  • •By week two. The routine work above runs on its own; anything sensitive stays with a named approver.
  • •At day 30. We review the impact metrics against your baseline:
  • •Catalog freshness: from about a month to under 1 h
  • •Owner assigned: from about 2 weeks to ~1 h
  • •Policy grant: from about a week to 5 min
  • •Cost. Start with a pilot ($7,500 one-time, credited in full against the first year). Scale is from $1,000 a month and Enterprise from $3,000 a month, billed annually, with unlimited seats, no usage meter and no markup on model spend. See pricing.

FAQ

Do we have to replace our catalog? No; agents can keep it current where it is.

Who approves definitions? Stewards, in Spellbook.

Does lineage stay current? It updates as agents change pipelines.