openfpa

Use when an Australian forecast needs official economic drivers - RBA cash rate and exchange rates, ABS CPI/WPI/retail/labour series - snapshotted with provenance for reproducible scenarios.

Use when forecasting cash for a GST-registered Australian entity - net GST positions, BAS settlement timing (monthly or quarterly), GST-free and input-taxed categories, 13-week cash impacts.

Use when forecasting payroll costs for an Australian employer - superannuation guarantee, state payroll tax, workers compensation, leave provisions, headcount plans with start dates and vacancies.

Use when onboarding an Australian company whose books are in Xero - request reports, detect GST-inclusive exports, map chart of accounts and tracking categories, reconcile to BAS and payroll before modelling.

Use when you want the model to learn from how its past forecasts actually turned out - scoring forecasts against the company's real actuals, backtesting assumptions on history, and proposing ratified improvements. Runs at/after monthly close.

Use when producing a board deck, investor update, or CFO briefing from an openfpa forecast - turning model output into a board-ready narrative and exportable artefacts.

Use when a human reviewing a forecast catches something off ("December always spikes", "you're double-counting deferred revenue", "that Q3 number was a one-time contract") - captures it as a durable, typed correction in the company's memory so future forecasts are grounded by it.

Use when answering "when do we run out of cash", building a 13-week cash forecast, sizing a credit line, or analysing near-term liquidity and payment timing in openfpa.

Use when interpreting financial actuals, reviewing margins or cash, drawing conclusions from a P&L or balance sheet, or about to tell someone a number means something - the judgement layer that separates "AI that does maths" from "AI that thinks like a CFO."

Use when wiring a company's real numbers into an openfpa model - from local spreadsheets (P&L, balance sheet, AR/AP ageing, inventory), a live system via MCP or API (QuickBooks, NetSuite), public filings (10-K/10-Q), or anything else. Not married to one source - build the ingestion for whatever the company has; produces one normalised account-amount shape the rest of the toolkit reads.

Use when the user wants their model in Excel with real working formulas - "export this to Excel", "a workbook I can hand my board", "something that recalculates when I change an assumption". Produces a live-formula workbook generated from the model structure and verified against the engine before delivery.

Use when starting FP&A work for a new company, onboarding a business into openfpa, or asked to "understand my business / set up a model for us" before any forecasting - produces a durable business profile and generates business-specific skills.

Use when running a month-end close, refreshing a forecast with the latest actuals, computing plan-vs-actual variance, or producing a "how did the month go" analysis in openfpa.

Use when you run FP&A for several clients and want your practice to compound - mines patterns that generalise across your same-type clients, validates them by leave-one-out cross-client backtesting, and promotes ratified priors and skills into a local library that seeds every new client. Local only, and each promotion needs an approval you record first.

Use after forecasts have scored actual outcomes and you want the AI to run bounded autonomous champion/challenger research epochs, discard weak candidates, and propose only evidence-backed model promotions.

Use when building a new openfpa forecast model from a company's financials - a trial balance, a P&L export, or a pasted income statement - and you need a runnable config to exist before any forecasting or analysis.