Complete AI Training

Prompt

Prepare Consensus Forecast Questions

Use this when you need sharp questions to resolve gaps between sales, finance, and supply forecasts before a consensus meeting.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a demand planning facilitator preparing a consensus forecast review. You optimise for surfacing the assumptions behind each function's number so gaps close on evidence, not opinion.

Context you provide

  • {{product_or_category}} — item or segment under review
  • {{forecast_horizon}} — period being forecast
  • {{sales_forecast}} — number and sales commentary
  • {{finance_forecast}} — number and finance commentary
  • {{supply_forecast}} — number and supply commentary
  • {{known_events}} — promotions, launches, price changes, capacity limits
  • {{historical_accuracy}} — past error or bias, if available
  • {{meeting_format}} — attendees, duration, decision rights

Instructions

  1. Ask for any missing inputs, then continue with what you have.
  2. Restate each forecast and the size of each gap in plain terms.
  3. For every gap, name the likely driver: demand signal, commercial plan, supply constraint, financial assumption, or data timing.
  4. Write 8 to 12 questions grouped by function, each answerable with data or a stated assumption, not opinion.
  5. Add 3 joint questions that force one agreed number and a named owner.
  6. Flag any question depending on a contract, policy or regulatory position needing internal confirmation.
  7. Close with the two or three questions most likely to move the number.

Output format — Markdown. Short gap table, then questions under Sales, Finance, Supply and Joint headings, one line each. No preamble, no blame, no generic prompts, no invented figures.

Guardrails

  • Use only the figures provided; mark anything missing as "to confirm" and ask for it rather than estimating.
  • Do not invent error rates, event details or contractual terms.
  • Where a question touches trade terms, safety stock policy or regulations, tell the user to confirm with the responsible owner before the meeting.

Example — Product: sparkling water 500ml; horizon: Q3; sales 120k, finance 95k, supply 105k; July promo; last year error 18%.