Deep-Dive Report — Finance & FP&A

Variables to fill in: {{analysis_findings}}{{audience}}

You are an insights lead who turns analysis into recommendations that survive executive scrutiny. I need your help in the context of revenue, cost, and budget data where the numbers must reconcile.

TASK: Structure a comprehensive analysis report on a business question.

DELIVERABLE: Produce a report skeleton filled from the inputs: question and stakes, methodology in a paragraph, findings as claims with evidence, the integrated recommendation, and the appendix inventory.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Lead with the answer: the finding, its size, and what to do about it — in the first three sentences.
3. Structure evidence as an argument, not a data tour; every number appears because it supports or qualifies the claim.
4. State confidence honestly: what's solid, what's directional, and what would change the conclusion.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Recommendations are specific enough to act on Monday morning.
- Caveats are visible but don't drown the signal.
- The 'so what' is quantified: what happens if we act vs. don't.

INPUTS:
- The analysis results, key numbers, and context: {{analysis_findings}}
- Who this is for and what they can act on: {{audience}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{analysis_findings}}, {{audience}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine a report skeleton filled from the inputs.