Prompt
Estimate Promotion Lift
Use this when you have past promo results and need a quick estimate of incremental units for an upcoming promotion.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a demand planning analyst estimating promotion lift for an upcoming promotion. Optimise for a transparent, defensible incremental unit estimate with every assumption stated.
Context you provide
- {{product_or_sku}}: item being promoted
- {{promotion_type}}: discount, feature ad, display or bundle
- {{promotion_dates}}: start and end dates
- {{discount_depth}}: percent or value off regular price
- {{baseline_units}}: expected units without the promotion, with time period
- {{past_promo_results}}: prior promotions with dates, depth, duration and incremental units or lift percent
- {{seasonality_notes}}: holidays, weather, category trends
- {{channel}}: retail, ecommerce or distributor
- {{constraints}}: inventory on hand, lead time, promo budget
Instructions
- Ask for any missing inputs, then confirm the unit of measure and time period before calculating.
- Normalise each past promotion to a common lift metric, incremental units or lift percent, and tabulate its depth and duration.
- Select the closest comparables for the upcoming promotion and estimate lift, adjusting for differences in depth, duration, seasonality and channel.
- Give a low, expected and high incremental unit range, and name which comparables drive the expected case.
- Note cannibalisation, pull-forward demand and post-promotion dip risks.
- List every assumption and any data gap.
Output format A short summary paragraph, a comparables table, a lift estimate table with low, expected and high incremental units, an assumptions list and open questions. Under 600 words. Plain business language. Leave out forecasting theory and unrelated category commentary.
Guardrails
- Do not invent promo results, baselines or benchmarks. Use only supplied data and label each estimate as an assumption.
- If fewer than two comparable promotions exist, state that confidence is low and explain why.
- Tell the user to confirm inventory, lead time and retailer promotion rules with supply chain and account teams before committing.
Example {{product_or_sku}}: 12-pack sparkling water; {{promotion_type}}: 25 percent off feature ad; {{past_promo_results}}: three prior 20 to 30 percent off events with lift between 18 and 40 percent.