13-Week Cash Flow Forecast: See Every Tight Week Before It Arrives
Turn your open AR, open AP, payroll, and recurring bills into a rolling 13-week cash forecast — weekly inflows, outflows, and ending cash — with low-cash weeks flagged and the controller approving before anyone sees the number.
A logged-in tool where you import open AR, AP, payroll, and recurring items, the agent projects 13 weeks of inflows, outflows, and ending cash, flags low- and negative-cash weeks, the controller reviews the assumptions and approves, and you export the forecast plus a forecast-vs-actual variance.
Before you start
- A Supabase account (free)
- A Vercel account (free)
- A Resend account (free)
- Exports of your open AR, open AP, and payroll schedule (CSV is fine)
- Your starting bank balance
- Claude Code or any AI coding agent
The problem this kills
When cash is tight, the question that matters is never "what did we earn last quarter?" It's "do we have enough in the bank on the week we run payroll, pay the big supplier, and the customer who promised to pay is two weeks late?" Most teams answer that question in a fragile spreadsheet that one person rebuilds every Friday — pasting in an AR aging, an AP aging, the payroll calendar, and a column of guesses about who will actually pay and when.
That spreadsheet breaks the moment it matters most. Formulas drift. Last week's "actual" never gets compared to what was forecast. The starting balance is keyed in from a stale bank screenshot. Nobody can see how a single slipped collection cascades into a negative week six weeks out. And because it lives on one laptop, when that person is on vacation, cash visibility goes dark.
A 13-week cash forecast is the single most valuable financial tool a tight-cash business has. It deserves to be a real, governed application — not a workbook held together with hope.
What you'll build
A simple internal web app for your finance team. You import your open AR (with the date you expect each customer to actually pay, not the invoice due date), your open AP (with due dates), your payroll schedule, and your recurring items — rent, loan payments, tax remittances, subscriptions. You enter the starting bank balance.
The tool buckets every expected inflow and outflow into the right week, applies your collection-rate assumptions (because not everyone pays on the promised date), and projects weekly inflows, weekly outflows, and ending cash for the next 13 weeks. It flags any week that goes negative or dips below your minimum-cash cushion. The controller reviews the weekly assumptions, adjusts the ones that look wrong, and approves the forecast before it's published or shared. Each week, the window rolls forward and the tool compares what you forecast against what actually happened, so the forecast gets sharper over time.
What's inside the Implementation Plan
The downloadable plan is a step-by-step file you paste into an AI coding agent. It opens by interviewing you about your business — how you collect, who your slow payers are, how your AR/AP exports are actually shaped, your pay-cycle cadence, your minimum-cash rule, and the messy exceptions (deposits, partial payments, post-dated checks). It reflects a short tailored spec back to you and gets your thumbs-up before it builds anything, so the forecast matches how your cash really moves — not a generic template.
From there it walks the agent through the data model, the AR/AP/payroll import, the weekly bucketing engine with collection-rate assumptions, the low-cash flagging, the controller approval gate, the weekly roll-forward, and the forecast-vs-actual variance report. Every step ends with a ready-to-copy prompt. There's a full "No API yet?" path that uses Google Sheet / CSV imports as the data source and produces a clean CSV export — so you can build and run the whole thing this weekend regardless of what accounting system you're on.
The governance it includes (this is the point)
This is a treasury tool, so the controls aren't optional. The plan builds in login so only your finance team can use it, row-level security so you only ever see your own organization's numbers, a complete audit trail of who changed which assumption and who approved which forecast, a hard human-approval gate so no forecast is published until the controller signs off on the inflow/outflow assumptions, and duplicate guards so the same invoice or payroll run can't be counted twice when you re-import.
Who it's for
Controllers, treasury and FP&A staff, and finance-owning founders — especially anyone managing through a tight-cash stretch who needs trustworthy weekly cash visibility and is tired of rebuilding a brittle spreadsheet every Friday. If you can explain how your customers actually pay and when your big bills hit, you can build this.
You've got this — start with the plan, paste the first prompt, and answer the interview. You'll have your first 13-week projection on screen before the weekend's out.