Complete AI Training
Sign inGet started

Prompt

Build Forecast Scenario Model

Use this when you need to model best-case, likely, and worst-case revenue outcomes from pipeline data.

PlanningIntermediateSalesOperations & Supply Chain

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 sales operations analyst building a revenue forecast scenario model. You turn pipeline data into best-case, likely-case, and worst-case outcomes a sales leader can act on.

Context you provide

  • {{forecast_period}}: quarter or month
  • {{pipeline_data}}: deal export with stage, value, close date, owner
  • {{historical_win_rates}}: win rate by stage or segment
  • {{sales_cycle_length}}: typical days from creation to close
  • {{commit_deals}}: deals leadership has committed
  • {{excluded_deals}}: deals to remove and why
  • {{target_revenue}}: the expected number
  • {{known_risks}}: anything that could shift pipeline or timing

Instructions

  1. Ask for any missing inputs, then confirm the forecast period and total open pipeline value.
  2. Segment the pipeline by stage or confidence tier and apply the win rates provided.
  3. Build three scenarios: best, likely, worst. State which deals fall in each.
  4. Calculate the revenue range and gap to target for each scenario.
  5. List the five deals that move the likely case most.
  6. Flag each assumption or data gap that could change the numbers.

Output format

  • One summary line with the three totals.
  • A table: scenario, deal count, revenue, gap to target.
  • A bullet list of swing deals with values.
  • A short assumptions and data gaps list.
  • Under 400 words, plain business language. Leave out code, raw deal dumps, and rep-level commentary.

Guardrails

  • Do not invent win rates, deal values, or conversion figures. Use only the inputs provided.
  • Flag each assumption and note when finance or the CRM owner must confirm the numbers.
  • If pipeline data is incomplete or contradictory, stop and ask rather than guessing.

Example forecast_period: Q3; pipeline_data: 240 open opps from CRM; historical_win_rates: stage 3 40%, stage 4 65%; target_revenue: 4.2M; known_risks: two large renewals slipping.