Use case
Use case3 min readBy The Data Workers Team

Population health data, run by agents

Registries and risk scores rebuild from EHR, claims and social data monthly, and care managers work from stale lists. Here is how Data Workers runs it instead.

Key takeaways

  • •The problem today. Registries and risk scores rebuild from EHR, claims and social data monthly, and care managers work from stale lists.
  • •What changes. Agents keep registries current from every source and verify risk inputs before care teams act.
  • •What stays with your people. Changes to cohort and risk definitions: they decide who gets care management.
  • •The result. Care managers work from lists that are days old, not months.

The problem today

Registries and risk scores rebuild from EHR, claims and social data monthly, and care managers work from stale lists.

What changes with Data Workers

Agents keep registries current from every source and verify risk inputs before care teams act.

The workflow: Data Ingestion agent (get_connector_status) → Pipeline Building agent (generate_pipeline) → Quality Monitoring agent (set_sla) → Data Security agent (scan_pii).
Fig. 1:The workflow: Data Ingestion agent (get_connector_status) → Pipeline Building agent (generate_pipeline) → Quality Monitoring agent (set_sla) → Data Security agent (scan_pii).

The workflow, step by step

  1. 1.The Data Ingestion agent calls get_connector_status and lands EHR, claims and SDOH data.
  2. 2.The Pipeline Building agent calls generate_pipeline and maintains registries.
  3. 3.The Quality Monitoring agent calls set_sla and keeps inputs fresh.
  4. 4.The Data Security agent calls scan_pii and classifies PHI.

The impact metrics we move

  • •Registry refresh: from about a month to 1 day
  • •New cohort definition: from about 2 weeks to 8 h
  • •Feed gap detected: from about a week to ~1 h
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

  • •Registries refresh continuously, so outreach reaches patients who need it now.
  • •Risk inputs are verified before scoring, so care teams trust the list.

Where your people stay in charge

Changes to cohort and risk definitions always go to a named approver, because they decide who gets care management. Everything starts at L1, observing only, and autonomy rises only on evidence.

The pilot

  • •Scope. One registry refreshed continuously.
  • •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:
  • •Registry refresh: from about a month to 1 day
  • •New cohort definition: from about 2 weeks to 8 h
  • •Feed gap detected: from about a week to ~1 h
  • •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 systems and providers 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.