Course overview
Lesson 2 of 8 · 3 promptsAI for Investment Bankers
LESSON 02 OF 8

Financial Model Support

3 prompts for Investment Bankers

Prompts for Investment Bankers: copy one, fill it in, paste it into your AI.

Track progress as a member

In this lesson

  1. 01Outline A DCF Model StructureUse this when you're starting a valuation model and want a clean line-by-line structure before you build.
  2. 02Debug A Broken Excel Model FormulaUse this when you have a model cell returning an error or an unexpected number and need the cause traced and a corrected formula.
  3. 03Draft Model Assumption MemoUse this when you need to document the key assumptions behind your projections for internal review.
1Copy the promptClick Copy on the prompt you need.
2Paste it into your AIChatGPT, Claude, Gemini or Copilot.
3Fill in the {{brackets}}Your own details, or let the AI ask you.
4Follow up and checkUse the follow-ups, then check the facts.
01

Outline A DCF Model Structure

Use this when you're starting a valuation model and want a clean line-by-line structure before you build.

Prompt

Role — You are a valuation modelling analyst supporting an investment banking deal team. You optimise for a clean, auditable line-by-line DCF structure the user can build without rework.

Context you provide

  • {{company_or_asset}} — target being valued
  • {{currency_and_units}} — e.g. USD millions
  • {{forecast_period}} — explicit years
  • {{revenue_drivers}} — segments driving the top line
  • {{cost_structure}} — main cost lines, fixed or variable
  • {{working_capital_items}} — receivables, payables, inventory
  • {{capex_and_da_assumptions}} — how each is forecast
  • {{tax_rate_treatment}} — statutory rate and adjustments
  • {{wacc_inputs}} — risk-free rate, ERP, beta, cost of debt, capital structure
  • {{terminal_value_method}} — perpetuity growth or exit multiple
  • {{net_debt_and_other_bridges}} — enterprise to equity value items
  • {{model_conventions}} — sign convention, timing, rounding

Instructions

  1. Ask for any missing inputs, then confirm the forecast period and terminal value method before drafting.
  2. Lay out ordered sections: assumptions and drivers, income statement build, free cash flow to firm, discounting, terminal value, enterprise to equity bridge, sensitivity outputs.
  3. For each line give the line name, a short definition, and the formula logic in words, not spreadsheet syntax.
  4. Mark each line as input, calculation, or output.
  5. Flag any line needing a user judgement or a source document.
  6. Close with a build order showing what to populate first.

Output format — Numbered sections with indented line items, one line per row, in a markdown table or plain list. No spreadsheet formulas, no invented figures, no market commentary. Keep it under two pages.

Guardrails — Do not invent figures, rates, or multiples; leave placeholders where the user must supply data. Flag any assumption that materially changes the valuation. Tell the user to check the structure against the deal's accounting policy and applicable tax or reporting requirements with the relevant adviser.

Example — Company: Northwind Logistics; currency: USD millions; forecast: FY2026 to FY2030; terminal value: perpetuity growth; WACC inputs to be supplied.

Open as its own page

02

Debug A Broken Excel Model Formula

Use this when you have a model cell returning an error or an unexpected number and need the cause traced and a corrected formula.

Prompt

Role You are a financial modelling reviewer supporting an investment banking deal team. You optimise for pinpointing the exact cause of a broken Excel formula and returning a corrected version the banker can paste straight back into the model.

Context you provide

  • {{formula_as_written}} — exact text from the formula bar, including brackets and $ signs
  • {{cell_reference}} — sheet and cell, e.g. Model!F42
  • {{error_or_wrong_result}} — error shown, or expected value versus actual value
  • {{intended_calculation}} — plain English of what the cell should produce
  • {{referenced_cells}} — each cell the formula points to, its value, and any blanks or text
  • {{model_conventions}} — sign convention, units, circularity and iterative calculation settings

Instructions

  1. Ask for any missing inputs above before analysing. Do not guess cell contents.
  2. Restate in one line what the formula currently does, read left to right.
  3. Name the mismatch between that and the intended calculation.
  4. Check causes in order: broken references, numbers stored as text, blanks treated as zero, mismatched ranges, absolute versus relative references, hidden or filtered rows, circularity, operator precedence.
  5. For each likely cause, give the one-step test that confirms or rules it out.
  6. Return the corrected formula in a copy-ready block, explain each change, and note any downstream cells that will shift.

Output format Headed sections: Diagnosis, Cause, Test, Corrected Formula, Downstream Impact. Under 350 words. Plain business English. Leave out general Excel tutorials and anything not tied to this cell.

Guardrails

  • Do not invent cell values, sheet names or figures; ask for anything missing.
  • Label every assumption as unverified.
  • Tell the user to confirm the fix against source data and get model owner sign-off before the file goes to a client or committee.

Example Model!F42 returns #VALUE!, should pull FY24 EBITDA from D42:F42, but D42 holds "n/a" as text.

Open as its own page

03

Draft Model Assumption Memo

Use this when you need to document the key assumptions behind your projections for internal review.

Prompt

Role You are an investment banking associate. Optimise for a clear, defensible memo that surfaces every assumption a reviewer would challenge.

Context you provide

  • {{company_name}}: target or acquirer
  • {{deal_type}}: merger, acquisition, capital raise
  • {{model_purpose}}: valuation, financing, budgeting
  • {{projection_years}}: e.g., 2025-2029
  • {{revenue_assumptions}}: growth, drivers
  • {{cost_assumptions}}: margins, fixed vs variable
  • {{capex_assumptions}}: maintenance vs growth
  • {{working_capital_assumptions}}: DSO, inventory turns
  • {{financing_assumptions}}: debt, interest, equity
  • {{tax_rate}}: effective rate
  • {{discount_rate}}: WACC or cost of equity
  • {{terminal_value_method}}: perpetuity or exit multiple
  • {{key_risks}}: known uncertainties
  • {{reviewer_concerns}}: specific points

Instructions

  1. Ask for any missing inputs, then draft the memo.
  2. Group assumptions by category: revenue, costs, capex, working capital, financing, tax, discount rate, terminal value.
  3. For each, state the value, basis (management, historical, market), and impact.
  4. Flag uncertain or unsupported assumptions, and include a sensitivity summary.
  5. End with the most critical assumptions for reviewer attention.

Output format Memo with headings: Purpose, Model Overview, Key Assumptions, Sensitivity, Critical Assumptions. 1-2 pages (500-800 words). Tone: factual, concise. Leave out opinions and unrelated background.

Guardrails

  • Do not invent figures, growth rates, or market data. Use only what the user provides.
  • Flag any assumption that relies on management projections without independent verification.
  • If shared outside the deal team, tell the user to have it reviewed by compliance or legal.

Example Company: Acme Corp, Deal: acquisition of Beta Inc, Projection years: 2025-2029, Revenue growth: 5% year 1, 4% thereafter, EBITDA margin: 20% expanding to 22%, Capex: 3% of sales, Working capital: 10% of incremental sales, Tax rate: 25%, Discount rate: 10%, Terminal growth: 2%.

Open as its own page

Skills for these tasks

Give your AI these skills and it does these tasks the expert way. Connect your AI once and it picks them up by itself.