Use case
Use case3 min readBy The Data Workers Team

FP&A and forecasting data, run by agents

Planning models wait on manual extracts, and actuals are a week old by the time the forecast runs. Here is how Data Workers runs it instead.

Key takeaways

  • •The problem today. Planning models wait on manual extracts, and actuals are a week old by the time the forecast runs.
  • •What changes. Agents keep planning inputs fresh, reconciled to actuals and governed, so forecasts run on current data.
  • •What stays with your people. Published forecasts: leadership plans on them.
  • •The result. Forecasts start from current actuals.

The problem today

Planning models wait on manual extracts, and actuals are a week old by the time the forecast runs.

What changes with Data Workers

Agents keep planning inputs fresh, reconciled to actuals and governed, so forecasts run on current data.

The workflow: Pipeline Building agent (generate_pipeline) → Quality Monitoring agent (set_sla) → Quality Monitoring agent (run_quality_check) → Autonomous Data-Conductor (verify_data).
Fig. 1:The workflow: Pipeline Building agent (generate_pipeline) → Quality Monitoring agent (set_sla) → Quality Monitoring agent (run_quality_check) → Autonomous Data-Conductor (verify_data).

The workflow, step by step

  1. 1.The Pipeline Building agent calls generate_pipeline and maintains planning inputs.
  2. 2.The Quality Monitoring agent calls set_sla and keeps them fresh.
  3. 3.The Quality Monitoring agent calls run_quality_check and reconciles to actuals.
  4. 4.The Autonomous Data-Conductor calls verify_data and verifies before each cycle.

The impact metrics we move

  • •Planning input refresh: from about a week to ~1 h
  • •Actuals reconciled: from about 3 days to 15-20 min
  • •New driver added: from about a week 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

  • •Inputs refresh continuously, so forecasts are current.
  • •Drivers are governed, so planning and finance agree.

Where your people stay in charge

Published forecasts always go to a named approver, because leadership plans on them. Everything starts at L1, observing only, and autonomy rises only on evidence.

The pilot

  • •Scope. Planning inputs for one business unit.
  • •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:
  • •Planning input refresh: from about a week to ~1 h
  • •Actuals reconciled: from about 3 days to 15-20 min
  • •New driver added: from about a week 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 finance and accounting 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.