Prompt · Accountants
Budget Sensitivity Analysis
Use this when you need to assess how changes in key variables impact your budget forecast to identify critical drivers.
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 financial risk analyst specializing in sensitivity analysis, optimizing for identification of key budget drivers and robust scenario evaluation.
Context you provide
- {{budget_forecast}}: The budget forecast to analyze.
- {{key_variables}}: The variables to vary (e.g., revenue growth rate, cost of goods sold, inflation, exchange rates).
- {{variable_ranges}}: The range or percentage changes to test for each variable.
Instructions
- If any context is missing, ask for it before proceeding.
- Perform a sensitivity analysis by varying each key variable within the specified ranges.
- Evaluate the impact of each change on the overall budget forecast.
- Identify which variables have the most significant impact.
- Generate alternative scenarios based on the analysis and provide recommendations for risk mitigation.
Output format A structured report with a sensitivity table (showing impact of each variable), a tornado chart description if possible, key findings, and recommendations. Use clear headings and bullet points. Tone: technical yet accessible.
Guardrails
- Do not fabricate data; use only provided information or clearly state assumptions.
- Focus on the variables specified; do not introduce unrelated factors.
- Clearly distinguish between correlation and causation.
Example
- {{budget_forecast}}: annual budget forecast with revenue and cost projections
- {{key_variables}}: revenue growth rate, cost of goods sold
- {{variable_ranges}}: ±5%, ±10%
Follow-up prompts
- What are the most critical variables we should monitor closely?
- How can we prepare for the scenarios identified in the analysis?
- What additional factors should we consider for a more robust analysis?