Use case
Use case3 min readBy The Data Workers Team

Portfolio monitoring data, run by agents

Holdings, exposures and performance come from custodians, OMS and risk systems that disagree each morning. Here is how Data Workers runs it instead.

Key takeaways

  • •The problem today. Holdings, exposures and performance come from custodians, OMS and risk systems that disagree each morning.
  • •What changes. Agents reconcile holdings across sources before the open and serve one governed exposure view.
  • •What stays with your people. NAV and risk inputs: they carry accountability.
  • •The result. PMs see one reconciled view before the open.

The problem today

Holdings, exposures and performance come from custodians, OMS and risk systems that disagree each morning.

What changes with Data Workers

Agents reconcile holdings across sources before the open and serve one governed exposure view.

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

The workflow, step by step

  1. 1.The Data Ingestion agent calls get_connector_status and lands custodian and OMS data.
  2. 2.The Quality Monitoring agent calls run_quality_check and reconciles holdings.
  3. 3.The Incident Debugging agent calls get_root_cause and traces breaks.
  4. 4.The Data Context & Catalog agent calls define_business_rule and governs exposure.

The impact metrics we move

  • •Holdings reconciled: from about 8 hours to under 1 h
  • •Break traced: from about 4 hours to 8-15 min
  • •Exposure question: from about a day 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

  • •Holdings reconcile on every load, so breaks are found before the open.
  • •Exposure is governed, so PM tools and risk agree.

Where your people stay in charge

NAV and risk inputs always go to a named approver, because they carry accountability. Everything starts at L1, observing only, and autonomy rises only on evidence.

The pilot

  • •Scope. Reconciliation for one custodian.
  • •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:
  • •Holdings reconciled: from about 8 hours to under 1 h
  • •Break traced: from about 4 hours to 8-15 min
  • •Exposure question: from about a day 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 financial services 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.