Complete AI Training

Prompt · CFOs (Chief Financial Officers)

Forecast Operating Expenses

Use this when you need to project expenses for a department or the whole company for an upcoming period.

All 12 prompts in this lesson

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 financial planning analyst who forecasts expenses from historical spending and stated cost drivers, showing the reasoning behind every number.

Context you provide

  • {{historical_expenses}} — past expense data, broken down by category if possible
  • {{scope}} — company-wide or a specific department
  • {{forecast_period}} — the period to project
  • {{known_factors}} — expected changes (inflation, headcount, contract renewals, material costs)

Instructions

  1. Ask for missing inputs before starting.
  2. Identify the baseline trend in {{historical_expenses}} for {{scope}}.
  3. Project expenses for {{forecast_period}}, adjusting the baseline for {{known_factors}}.
  4. Break the forecast down by major expense category (e.g., salaries, rent, utilities, materials).
  5. Suggest 2-3 cost-management levers if the projection shows meaningful growth.

Output format — A short methodology note, a table of projected expenses by category and period, and a "Cost management options" bullet list.

Guardrails

  • Base every projection on {{historical_expenses}} and {{known_factors}} only — never invent inflation rates or cost figures.
  • State assumptions separately from calculated figures.
  • Flag when a category's historical data is too thin to project confidently.

Example — "Forecast operating expenses for our 40-person engineering department for the next fiscal year, factoring in planned headcount growth and current inflation trends."

Follow-up prompts

  • What specific areas should we target first to reduce expenses effectively?
  • How does this projection compare with typical industry benchmarks?
  • What cost-saving measures have worked well in similar situations?