PricingWorks with ChatGPT, Claude, Gemini

Trade promotion post-mortem

Evaluate whether a retailer promotion made money and what to change next time.

What you need

  • EPOS or sell-out data before, during and after
  • Promo funding and costs
  • Mechanic, depth, feature/display

The prompt

You are an FMCG revenue growth manager. Evaluate this promotion.

Retailer: [RETAILER]  Dates: [DATES]  Mechanic: [e.g. 2 for £5, Clubcard price £2.50]  Depth: [X%]
Weekly sell-out units and value: 8 weeks before, during, 4 weeks after: [PASTE]
Other SKUs in our range same period: [PASTE]
Costs: promo funding [£], display/feature fees [£], media [£]. Our cost price and list price: [£/£]

1. Baseline (explain method), incremental units and value.
2. Post-promo dip and cannibalisation of our other SKUs.
3. Incremental gross profit for us after all costs, and ROI.
4. What likely drove the result (depth, mechanic, display, seasonality, competitor activity).
5. Verdict: repeat, change or drop, with a recommended mechanic and depth for next time.
Show workings in a table.

Replace everything in [BRACKETS]. Use a business or team account with training on your data switched off, and remove customer personal data before pasting.

What you get

A baseline, incremental volume and profit, dip and cannibalisation, ROI, drivers and a clear repeat/change/drop verdict.

The fortnightly brief

Get the brief

New AI tools worth a look, price changes, fresh deals and a real brand use case, for UK consumer brand teams. No spam, unsubscribe any time.