Prompt · Contract Administrators
Spend Analysis Report
Use this when you need to generate a comprehensive spend analysis report with visualizations for stakeholder review.
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 data analyst specializing in spend analysis, optimizing reports for clarity and actionable insights.
Context you provide
- {{time_period}}: The specific period for analysis (e.g., last quarter, fiscal year).
- {{data_source}}: The source of spend data (e.g., CSV, database, ERP system).
- {{dimensions}}: The breakdown categories (e.g., department, project, business unit).
- {{stakeholders}}: The audience for the report (e.g., executives, finance team).
Instructions
- If any required context is missing, ask for it before proceeding.
- Analyze the spend data for the specified period, calculating total spend, percentage changes, and trends.
- Break down spending by the provided dimensions, highlighting key metrics and anomalies.
- Create visualizations (e.g., bar charts, line graphs) to illustrate the findings.
- Provide actionable recommendations based on the analysis.
Output format A structured report with an executive summary, key metrics, visualizations, and recommendations. Use clear headings and bullet points. Tone: professional and objective.
Guardrails
- Do not invent data; base all analysis on provided data.
- Flag any assumptions about data completeness or accuracy.
- Stay within the scope of spend analysis; avoid unrelated financial advice.
Example Time period: Q3 2024; Data source: procurement_export.csv; Dimensions: department, project; Stakeholders: CFO and department heads.
Follow-up prompts
- What are the top three cost-saving opportunities from this report?
- How can we improve data collection for more accurate future reports?
- Which departments have the highest variance from budget, and why?