Use case
Use case3 min readBy The Data Workers Team

Stars and quality data, run by agents

HEDIS and Stars measures depend on claims, lab, pharmacy and supplemental data from dozens of sources, and gaps are found weeks before submission. Here is how Data Workers runs it instead.

Key takeaways

  • •The problem today. HEDIS and Stars measures depend on claims, lab, pharmacy and supplemental data from dozens of sources, and gaps are found weeks before submission.
  • •What changes. Agents keep every measure input fresh and complete, flag gaps as they appear and document lineage for each measure.
  • •What stays with your people. Submitted measure rates: they carry regulatory accountability.
  • •The result. Gaps are closed months before submission, with lineage ready for audit.

The problem today

HEDIS and Stars measures depend on claims, lab, pharmacy and supplemental data from dozens of sources, and gaps are found weeks before submission.

What changes with Data Workers

Agents keep every measure input fresh and complete, flag gaps as they appear and document lineage for each measure.

The workflow: Connectors agent (get_connector_status) → Quality Monitoring agent (set_sla) → Data Context & Catalog agent (trace_cross_platform_lineage) → Autonomous Data-Conductor (verify_data).
Fig. 1:The workflow: Connectors agent (get_connector_status) → Quality Monitoring agent (set_sla) → Data Context & Catalog agent (trace_cross_platform_lineage) → Autonomous Data-Conductor (verify_data).

The workflow, step by step

  1. 1.The Connectors agent calls get_connector_status and lands lab, Rx and supplemental feeds.
  2. 2.The Quality Monitoring agent calls set_sla and tracks freshness per measure input.
  3. 3.The Data Context & Catalog agent calls trace_cross_platform_lineage and documents each measure's lineage.
  4. 4.The Autonomous Data-Conductor calls verify_data and verifies measure inputs before rate runs.

The impact metrics we move

  • •Supplemental feed onboarded: from about 3 weeks to 2 days
  • •Measure gap detected: from about a month to ~1 h
  • •Lineage for a measure: from about a week to minutes
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

  • •Freshness and completeness are tracked per measure input, so gaps surface while there is still time to close them.
  • •Lineage is documented for every measure, so audit evidence is ready.

Where your people stay in charge

Submitted measure rates always go to a named approver, because they carry regulatory accountability. Everything starts at L1, observing only, and autonomy rises only on evidence.

The pilot

  • •Scope. Freshness and completeness on the top ten measures.
  • •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:
  • •Supplemental feed onboarded: from about 3 weeks to 2 days
  • •Measure gap detected: from about a month to ~1 h
  • •Lineage for a measure: from about a week to minutes
  • •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 health plans and payors hub · 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.