Use case
Use case3 min readBy The Data Workers Team

Cost of care data, run by agents

Trend analysis waits on monthly claims refreshes, lag adjustments are rebuilt by hand and every executive asks why PMPM moved. Here is how Data Workers runs it instead.

Key takeaways

  • •The problem today. Trend analysis waits on monthly claims refreshes, lag adjustments are rebuilt by hand and every executive asks why PMPM moved.
  • •What changes. Agents keep claims, eligibility and pharmacy data complete and lag-adjusted as they land, and trace every PMPM move to its drivers.
  • •What stays with your people. Published trend and PMPM numbers: they drive pricing and reserves.
  • •The result. Medical economics explains trend in days, not after the quarter.

The problem today

Trend analysis waits on monthly claims refreshes, lag adjustments are rebuilt by hand and every executive asks why PMPM moved.

What changes with Data Workers

Agents keep claims, eligibility and pharmacy data complete and lag-adjusted as they land, and trace every PMPM move to its drivers.

The workflow: Data Ingestion agent (get_connector_status) → Quality Monitoring agent (run_quality_check) → Data Context & Catalog agent (define_business_rule) → Incident Debugging agent (diagnose_incident).
Fig. 1:The workflow: Data Ingestion agent (get_connector_status) → Quality Monitoring agent (run_quality_check) → Data Context & Catalog agent (define_business_rule) → Incident Debugging agent (diagnose_incident).

The workflow, step by step

  1. 1.The Data Ingestion agent calls get_connector_status and lands claims, eligibility and Rx feeds.
  2. 2.The Quality Monitoring agent calls run_quality_check and checks completeness by month of service.
  3. 3.The Data Context & Catalog agent calls define_business_rule and applies governed PMPM and trend definitions.
  4. 4.The Incident Debugging agent calls diagnose_incident and explains unexpected trend moves.

The impact metrics we move

  • •Monthly trend refresh: from about 2 weeks to 1 day
  • •PMPM move explained: from about a week to 2 h
  • •New cohort cut: from about 5 days to 4 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

  • •Completeness checks by month of service run on every load, so trend is never reported on an incomplete month.
  • •PMPM, trend and utilization definitions are governed, so finance and medical economics report one number.

Where your people stay in charge

Published trend and PMPM numbers always go to a named approver, because they drive pricing and reserves. Everything starts at L1, observing only, and autonomy rises only on evidence.

The pilot

  • •Scope. Completeness and trend definitions on one product line.
  • •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:
  • •Monthly trend refresh: from about 2 weeks to 1 day
  • •PMPM move explained: from about a week to 2 h
  • •New cohort cut: from about 5 days to 4 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 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.