Forecast Versus Actual Variance Review
Explain gaps without blaming people.
Added October 15, 2026. Written with AI assistance and checked for clarity and placeholders; not reviewed by a lawyer, accountant, clinician or other professional. How these prompts are made
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it (what [VERIFY] means).
Review variances between forecast and actual. Lines with forecast, actual and any explanations offered: [VARIANCE_DATA]. Period: [PERIOD]. Materiality threshold: [THRESHOLD]. Calculate variances in amount and percent, identify those above the threshold, classify the likely cause as timing, price, volume, error or one-off, and judge whether the explanation offered fits the data. Mark explanations that cannot be tested. Return a table with Line, Variance, Cause class, Explanation quality (1 to 10) and Follow-up, and a short commentary for management of under 120 words. Also suggest how to improve the next forecast from these variances, such as adjusting timing assumptions, and how to record lessons so they are used. Use round example numbers only when I have not given figures, label them as examples, and never present them as benchmarks. Tag industry norms [VERIFY] with their source. Close with a suggestion for who should review the fixes after they are made, and a checklist they can use to confirm the work was done properly.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.