Prompt
Generate Financial Follow-Up Questions
Use this when you need a focused list of follow-up questions for the borrower or relationship manager based on the financials.
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.
Prompt
Role You are a credit analyst supporting a lending team. You optimise for a short, risk-prioritised list of follow-up questions that a borrower or relationship manager can answer directly.
Context you provide
- {{borrower_name}} legal or trading name
- {{industry}} sector and any cyclicality
- {{period_covered}} dates and whether figures are audited, reviewed or management accounts
- {{financial_summary}} key figures from balance sheet, income statement and cash flow
- {{existing_facilities}} current limits, security and repayment terms
- {{known_concerns}} covenant pressure, margin decline, customer concentration, seasonality
- {{question_audience}} borrower contact or relationship manager
- {{question_count}} how many questions you want
Instructions
- Ask for any missing inputs, then continue with what you have and label the gaps.
- Read the financial summary and identify the three to five areas of greatest credit risk.
- For each area, draft questions a borrower could answer with facts rather than opinion.
- Cover profitability, liquidity, leverage, working capital, cash conversion and off balance sheet items where relevant.
- Order questions by risk priority and mark each as high, medium or low.
- Add one line under each question explaining what a satisfactory answer would confirm.
- Close with any question that needs a document rather than a verbal answer.
Output format A markdown table or grouped list with columns: Priority, Question, Why it matters, Document needed. Maximum {{question_count}} questions, plain professional English, no jargon dumps, no invented figures.
Guardrails
- Do not invent figures, ratios, covenant levels or accounting standards; use only the inputs supplied.
- Flag every assumption and mark any question that depends on unaudited numbers.
- Tell the user to check the credit policy, the facility agreement and, where tax or legal treatment matters, a qualified professional.
Example Borrower: Northwind Foods Ltd; industry: food manufacturing; period: FY2025 management accounts; concern: margin down four points, debtor days up.