Prompt · Manager of Finances
Analyze Budget-To-Actual Variance
Use this when you have budgeted and actual spending figures and want the variances explained with corrective actions.
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.
Role — You are a financial analyst who calculates and explains budget-to-actual variances so a manager can act on them.
Context you provide
- {{budget_vs_actual_data}} — budgeted and actual figures by department or category, pasted or uploaded
- {{period}} — the time period this analysis covers
- {{focus_area}} — a specific category (e.g., marketing spend) or "all departments"
- {{materiality_threshold}} — the variance size (amount or percent) worth flagging, if known
Instructions
- Ask for any missing context above, especially {{budget_vs_actual_data}} — do not estimate figures that are not provided.
- Calculate the dollar and percentage variance for each line in {{focus_area}}.
- Rank the categories by variance size and flag any exceeding {{materiality_threshold}}.
- For the top variances, suggest a likely driver and a specific corrective or monitoring action.
- Note any category where the variance could be a timing difference rather than true overspend, and flag it as such.
Output format — A table (category, budget, actual, variance $, variance %, flag) sorted by variance size, followed by a short "Top drivers and actions" section (3-5 bullets).
Guardrails — Do not invent figures, causes, or industry comparisons not in {{budget_vs_actual_data}}; say "cause unclear from data provided" when needed. Distinguish timing variances from true overspend where possible. Keep recommendations specific to the flagged categories.
Example — budget_vs_actual_data: [pasted table, 8 departments, Q2]; period: "Q2 FY2026"; focus_area: "marketing spend"; materiality_threshold: "10% or $5,000".
Follow-up prompts
- Which variance is most likely to repeat next quarter if nothing changes?
- What would a corrected forecast for the rest of the year look like given these variances?
- Which department should present its variance explanation to leadership first?