Home · Business · Finance & Accounting · Invoicing & credit control
As of 13 August 2026, AI can calculate late payment interest on an overdue invoice.
This still needs a person who signs their name to it.
Can you do it?
5 minutesto a draft.
15 minutesto something you’d act on.
Cost, all in£0
Skill neededchat-fluent
Who has to check ityou
What the alternative costsThe supplied tool data gives no price for a human or software alternative.
If this goes wrong: you demand the wrong amount, weaken your credit-control position or create a dispute with the customer.
What to actually do
Hand it to a person
The route this page recommends
A person who owns the outcome does this end to end, worth it when the failure is dear.
Use a tool built for this
Second choiceDo it yourself
The distant thirdA chat interface, chat-fluent skill, and roughly 15 minutes until you can act on the result.
How to actually do it
- Open the overdue invoice, the customer contract or order terms, and your bookkeeping or invoice ledger.
- Gather the invoice amount, VAT treatment, invoice date, agreed payment terms, contractual interest wording, due date, payment dates and amounts, and the date up to which interest should be calculated.
- Open the relevant GOV.UK guidance and record the applicable statutory rate and the period for which it applies; paste the source wording or link into the prompt rather than asking the model to guess a current rate.
- Paste the prompt and the gathered facts into a chatbot, including every part-payment and any uncertainty about the due date or interest clause.
- Export or copy the model's table into a spreadsheet and independently recalculate each period using the outstanding balance, number of days and supplied rate.
- Compare the result and assumptions with the invoice ledger, contract and GOV.UK guidance, then have an accountant or solicitor check any disputed entitlement before you send the interest demand.
Prompt
Calculate late payment interest on this UK business invoice using only the facts and official rate information I provide. Invoice amount: [amount and currency] Invoice date: [date] Contractual payment terms: [terms] Due date: [date] Date payment was received, or calculation end date: [date] Payments received before the final payment: [dates and amounts, or none] Contractual interest clause: [paste it, or state none known] Applicable statutory rate information from GOV.UK or another official source: [paste the rate, the rate period and the source] Whether the customer and supplier are businesses: [details] First, state whether the supplied facts appear sufficient to calculate the amount. Do not decide that statutory interest is legally available if the facts do not establish that; instead, flag the missing fact or legal question. Calculate separate scenarios for contractual interest and statutory interest where both may be relevant. Show each rate period, outstanding balance, number of days, formula, daily amount, rounding method and subtotal in a table, then give the total interest and total amount due. State whether the calculation uses the invoice amount including or excluding VAT, and do not assume this where the documents do not say. Use no rates, dates or legal facts that I have not supplied, and identify every assumption. Tell me which figures I should compare with the invoice ledger and official GOV.UK guidance before sending a demand. This is not professional advice.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
What it gets wrong
- AI cannot establish from incomplete documents whether statutory interest is legally available for this customer and transaction.
- AI cannot reliably resolve conflicting payment terms, disputed invoices or unclear dates without your business context.
- AI can use a stale or incorrectly supplied rate if you do not provide and check the official rate for each period.
- AI does not take responsibility for the amount you demand or for the effect of an incorrect claim on the customer relationship.
- AI cannot replace an accountant or solicitor where the customer disputes the debt or the interest entitlement.
Even on a YES, the friction has a name: legal accountability, judgement under ambiguity and stakes of error.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 2 |
| Verification | 1 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 8 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT calculate late payment interest on an unpaid invoice?
- Yes, it can calculate the arithmetic if you provide the invoice amount, relevant dates, payments, interest basis and rate for each period. Check the result against your ledger and GOV.UK, because the tool does not decide whether you are legally entitled to claim the interest.
- What information do I need to calculate late payment interest?
- Gather the invoice and due dates, amount and VAT treatment, agreed payment terms, interest clause, payment history, calculation end date and the applicable official rate information. Include any part-payments and disputed dates, since both can change the calculation.
- Can I charge statutory interest on a late business payment?
- That depends on the transaction, the parties, the agreed terms and whether the statutory conditions apply. Use GOV.UK for the current guidance and ask an accountant or solicitor about a disputed or serious claim; this is not professional advice.
- How do I check an AI calculation of late payment interest?
- Recalculate each rate period in a spreadsheet using the outstanding balance and exact number of days, then compare the rate and legal basis with GOV.UK and the contract. Have an accountant or solicitor check the entitlement before sending a demand if the customer disputes the invoice.
Nearby answers
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.