Use case
Use case3 min readBy The Data Workers Team

Semantic layer and governed context, run by agents

Metric definitions live in dbt, BI tools, notebooks and people's heads, and every copilot answers from a different one. Here is how Data Workers runs it instead.

Key takeaways

  • •The problem today. Metric definitions live in dbt, BI tools, notebooks and people's heads, and every copilot answers from a different one.
  • •What changes. Data Context Wizard holds one governed definition of every metric and entity, with lineage and owners, and agents keep it current as pipelines change.
  • •What stays with your people. Changes to certified definitions: many teams depend on them.
  • •The result. Dashboards, copilots and agents answer from the same definitions.

The problem today

Metric definitions live in dbt, BI tools, notebooks and people's heads, and every copilot answers from a different one.

What changes with Data Workers

Data Context Wizard holds one governed definition of every metric and entity, with lineage and owners, and agents keep it current as pipelines change.

The workflow: Data Context & Catalog agent (define_business_rule) → Data Context & Catalog agent (trace_cross_platform_lineage) → Data Context & Catalog agent (mark_authoritative) → Data Access & Governance agent (check_policy).
Fig. 1:The workflow: Data Context & Catalog agent (define_business_rule) → Data Context & Catalog agent (trace_cross_platform_lineage) → Data Context & Catalog agent (mark_authoritative) → Data Access & Governance agent (check_policy).

The workflow, step by step

  1. 1.The Data Context & Catalog agent calls define_business_rule and reconciles and governs definitions.
  2. 2.The Data Context & Catalog agent calls trace_cross_platform_lineage and links each definition to its sources.
  3. 3.The Data Context & Catalog agent calls mark_authoritative and marks the source of truth.
  4. 4.The Data Access & Governance agent calls check_policy and applies access rules.

The impact metrics we move

  • •Conflicting definition reconciled: from about a month to 8 h
  • •Definition question: from about a day to seconds
  • •Lineage for a metric: from about 2 days to seconds
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.

What goes on autopilot

  • •Definitions update as agents change pipelines, so the layer never goes stale.
  • •Every answer carries provenance, so people can check where a number came from.

Where your people stay in charge

Changes to certified definitions always go to a named approver, because many teams depend on them. Everything starts at L1, observing only, and autonomy rises only on evidence.

The pilot

  • •Scope. Govern the top 25 metrics for one domain.
  • •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:
  • •Conflicting definition reconciled: from about a month to 8 h
  • •Definition question: from about a day to seconds
  • •Lineage for a metric: from about 2 days to seconds
  • •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.

Related: The data and IT page · The full team playbook

Related Posts

Use case

Account intelligence data, run by agents

Account data is split across CRM, billing, product usage and enrichment vendors that identify accounts differently. Here is how Data Workers runs it instead.

Use case

Accruals and prepaids data, run by agents

Accrual schedules live in spreadsheets, and missed or stale accruals surface in review. Here is how Data Workers runs it instead.

Use case

Agent governance and audit, run by agents

AI agents act on data with no consistent approval, record or rollback. Here is how Data Workers runs it instead.

Use case

Agentic controllership, run by agents

Controllers spend the month chasing reconciliations, approvals and evidence across ERP, billing and spreadsheets. Here is how Data Workers runs it instead.