As of 13 August 2026, AI can only partly calculate unit economics for your UK startup.

What to actually do

1. 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.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, power-user skill, and roughly 1 hour until you can act on the result.

   How to actually do it

   1. Open your accounting records, payment processor, marketing platforms and customer database, then gather a consistent period of revenue, refunds, discounts, payment fees, variable costs, fixed costs, sales and marketing spend, and new and retained customers.
   2. Create a spreadsheet with one row per period or customer cohort and columns for each input, recording the source, date range, whether VAT is included, and whether the figure is observed or estimated.
   3. Write down the unit you are measuring, such as one customer, order or subscription, and choose definitions for revenue, variable cost, acquisition spend, churn and retention before calculating anything.
   4. Paste the cleaned table and the completed prompt into ChatGPT, Claude, Gemini or Julius, and ask the model to return formulas, results, missing-data warnings and the three scenarios requested.
   5. Recalculate the headline metrics in your spreadsheet using the model's stated formulas, then compare each result with the source figures and investigate every difference.
   6. Change the uncertain assumptions one at a time in the spreadsheet, compare the effect on margin, lifetime value and payback, and send the final table to your accountant or finance lead if it will support a material funding, pricing or hiring decision.

   Prompt

   Calculate the unit economics for my UK startup from the data below. Use GBP and keep VAT treatment explicit. Do not invent, fill, or silently alter any figures. Separate observed figures from assumptions, flag missing data, and state the formula used for every metric. Calculate contribution margin per customer, customer acquisition cost, lifetime value only if the available retention data supports it, payback period, revenue per customer and any other useful unit metrics supported by the data. If a metric depends on a debatable definition, show the alternative definition and explain the difference. Produce a table with the inputs, formulas, results and confidence or data-quality notes. Then create conservative, base and optimistic scenarios by changing only assumptions I have identified, not factual inputs. Recalculate each scenario and identify which assumptions have the greatest effect. Check the arithmetic independently before presenting the result. Do not give tax, accounting or investment advice, and do not present forecasts as facts.
   
   Business model: [subscription, usage-based, marketplace, services or other]
   Unit being analysed: [customer, order, subscription, project or other]
   Period covered: [dates]
   Currency and VAT treatment: [details]
   Revenue by unit: [figures and source]
   Variable costs by unit: [figures and source]
   Fixed costs: [figures and source]
   New customers or units acquired: [figures and source]
   Sales and marketing spend: [figures and source]
   Retention, churn or repeat-purchase data: [figures and source]
   Refunds, discounts and payment fees: [figures and source]
   Other relevant costs or constraints: [details]
   Assumptions I approve for scenarios: [list]
   Questions about definitions or missing data: [list]

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.