CPD lab · AR, FP&A
13-week cash forecast
Build a 13-week cash forecast from the ageing, payroll and tax dates and a loan, with your AI tool, and catch the dates and one-offs it gets wrong.
Comes with AR, credit and cash and FP&A and forecasting, and with the year. 29 labs open now.
The brief
You are the finance analyst at Calderbrook Signs Ltd, which makes and maintains signs for hotels, retail parks and leisure sites. It is Monday 2 November 2026. The Finance Director wants a 13-week cash forecast before the bank review on Friday.
The pack has the forecast assumptions, the AR ageing, six months of customer payment history, the AP ageing, the VAT return for the September quarter, the loan agreement extract and the credit controller's notes. Every company and figure is invented, so you can paste it into any AI tool.
Use your AI tool to build the forecast, then check it. Follow the assumptions file exactly: every figure must come from it or from the files it points to. Add no buffers, growth or haircuts of your own.
Give one line per week, weeks 1 to 13. week is the week number (1 to 13). week_commencing is the Monday (dd/mm/yyyy). receipts and payments are the week's totals in pounds, as positive numbers. opening_cash is the previous week's closing cash (week 1 opens at 44,250.00), and closing_cash is opening_cash plus receipts minus payments. Write an overdrawn balance with a minus sign.
Dates matter more than averages here. Work out each customer's real payment habit from the history, and check every payroll, tax, rent and loan date against the calendar, including bank holidays.
Then write a short review note: what the AI got wrong, what you checked, and what goes to the Finance Director.
Objective: To be able to build and check a 13-week cash forecast prepared with an AI assistant, placing receipts by real customer payment behaviour and payments on their actual dates, and to explain the cash low point to the people who need to act on it.
What's in the pack
Every name, figure and email in the pack is invented. Use your own AI tool: Claude, ChatGPT, Copilot or Gemini.
forecast-assumptions.txt
The forecast assumptions, approved by the Finance Director
ar-ageing.csv
Open customer invoices at 2 November 2026 (8 invoices)
customer-payment-history.csv
Each contract customer's last six paid invoices (30 lines)
ap-ageing.csv
Open supplier invoices at 2 November 2026 (7 invoices)
vat-return-q3-2026.txt
VAT return for the quarter to 30 September 2026
loan-agreement-extract.txt
Term loan: repayment terms
sales-ledger-notes.txt
Credit controller's notes on October
The traps
The pack has 6 deliberate traps: cases where AI tools often get it wrong and a person must check. We don't list them here. Finding them is the job, and your feedback names each one you missed.
What you submit
- Your result, as a table with the columns week, week_commencing, opening_cash, receipts, payments, closing_cash.
- The prompt you used.
- A short review note, 150 to 350 words: what the AI got wrong, what you checked, and what goes to a person.
How it's marked
- Your result, checked line by line against the answer key60%
- Your review note, marked on traits40%
The review note's traits:
- Receipt timing tested against history
- Payment dates checked against the calendar
- The forecast rolls forward and ties
- The low point explained and escalated
- Real data kept out of personal accounts
Pass at 80. Under 80, read the feedback and try again. Then write your reflection and copy the entry for your CPD record.
Price
- AR, credit and cash, £79. The role track and its labs, this one included. No end date.
- FP&A and forecasting, £79. The role track and its labs, this one included. No end date.
- Everything for a year, £199. Every course, role track and lab for 365 days.
- Monthly, £19.99 a month, cancel any time. Every lesson, plus 8 marked tasks a month, across every course, role track and lab.
Buying for a team, or want a lab built on your own process? CPD for employers.