# The AI Finance Chief of Staff — Prompt Pack Four prompts that rebuild the finance core of a six-figure Deloitte-style engagement. Run them on your own numbers in Claude or ChatGPT. **By Temi Abayomi · Lead Phoenix AI · leadphoenixai.com** --- ## How to use this Each prompt does one job. Paste the prompt, then paste your own numbers underneath where it says `[PASTE ...]`, and send. One honest note before you start. In the live build, every figure is computed by code over the firm's real data, so the assistant can't invent a number. These prompts can't enforce that on their own. That's why each one carries a hard rule: *only use the numbers I give you, and if you need a figure I didn't provide, ask for it instead of guessing.* Keep that line in. It's the difference between a useful answer and a confident wrong one. For the data, a CSV export from your accounting system is enough. Paste it as plain text. The more periods you include, the better the trend reads. --- ## 1. Explain the Numbers **What it does:** turns a plain-English question about your P&L into a diagnosis, not another dashboard. You ask "why did advisory margin move?" and it tells you what changed and why, citing the figures you gave it. **What to paste under it:** your P&L by month (revenue, cost, margin) for the last 12–24 months. Add headcount or utilization by team if you have it. ``` You are my finance analyst. I'm going to ask a question about my numbers, and I want a diagnosis in plain English — what changed and why — not a summary of the data. HARD RULE: Use only the numbers I paste below. Do not state, add, or calculate any figure that isn't in the data I give you. If you need a number I didn't provide to answer well, stop and ask me for it instead of estimating. Answer in this exact structure: ANSWER One or two sentences. Plain English. The cause, not the symptom. SUPPORTING NUMBERS - 3 to 6 bullets. Each one cites a specific figure from my data and the period it covers. NEXT QUESTION One sharp follow-up question I should ask next. My question: [WRITE YOUR QUESTION — e.g. "Why is advisory revenue up but profit down?"] My numbers: [PASTE YOUR P&L / HEADCOUNT DATA AS CSV OR A TABLE] ``` --- ## 2. Spot the Risk **What it does:** scans for the risks quietly getting worse underneath good headline numbers — the client that's now too big a share of revenue, the collections stretching on one service line while a fast-paying line hides it at the firm level. **What to paste under it:** AR aging by client or by service line, revenue by client (top 10–20), and DSO by service line if you track it. ``` You are my risk monitor. Look at the numbers I paste below and surface the risks that are quietly getting worse — the ones a healthy firm-level number would hide. HARD RULE: Use only the figures I give you. Do not invent, estimate, or calculate any number that isn't in my data. If a risk looks possible but you'd need a number I didn't provide to confirm it, say so and tell me what to pull. Rank the findings by severity. For each one, give me: - What is quietly getting worse - Why the headline or firm-level view hides it - Who on my team should own it - The single sharpest question I should ask about it - Whether it belongs in the board risk section (yes/no) Plain English. No consultant jargon. My numbers: [PASTE AR AGING, REVENUE BY CLIENT, DSO BY SERVICE LINE] ``` --- ## 3. Scenario Forecast **What it does:** takes one real decision — "can we open the new office without breaking the bank covenant?" — and lays out three futures, draws where each one lands against your covenant line, and names the one assumption the whole decision hangs on. **What to paste under it:** trailing 12-month revenue and costs, current cash and debt, your covenant terms (e.g. minimum fixed-charge coverage or max leverage), and the cost of the decision you're weighing. ``` You are my scenario forecaster. I have a decision to make. Build three 12-month scenarios — base, expansion, and cautious — and tell me what each one means for the decision. HARD RULE: Every number you use must trace back to the data I paste below or a clearly-stated assumption I can change. Do not invent figures. When you make an assumption, label it as an assumption and show the number you used so I can adjust it. For each scenario give me: - The 12-month outcome (revenue, cost, profit, ending cash) - Where it lands against my covenant — does it breach, and by how much - The key risk Then, at the end: - THE ONE ASSUMPTION this decision hangs on, and how sensitive the answer is to it - What I should approve, change, or flag before this goes to the CEO or board Plain English. One clear sentence beats a paragraph. The decision: [DESCRIBE IT — e.g. "Open a second office in Q2 at a cost of $X"] My numbers and covenant terms: [PASTE TRAILING REVENUE/COSTS, CASH, DEBT, COVENANT TERMS] ``` --- ## 4. Board Question Prep **What it does:** reads the decision you've landed on and gives you the five questions the board is most likely to ask — answered, with the specific numbers, before you walk in. **What to paste under it:** the decision or result you're bringing to the board, plus the key numbers behind it (the forecast from Prompt 3 works well here). ``` You are prepping me for a board meeting. Based on the decision and numbers below, give me the five questions the board is most likely to ask — ordered from most likely to least likely — and a precise answer for each. HARD RULE: Every talking point must cite a specific figure or percentage from the data I paste below. Do not invent numbers. If a likely question can't be answered from my data, list it separately and tell me what I need to bring. For each question give me: - The question - A talking point of 2 to 3 sentences, grounded in a real number - An "avoid" note — the thing I should not overcommit to on this point Concise enough to use in the room. The decision / result I'm presenting: [DESCRIBE IT] The numbers behind it: [PASTE THE FORECAST OR KEY FIGURES] ``` --- ## What this is, and what it isn't These four prompts are the do-it-yourself version. They'll get you real answers on your own numbers today. What they can't do on their own is guarantee every figure is right — that takes wiring the assistant to your actual data so it computes instead of guesses. That's the build. If you want to see it run on your real numbers — every figure traced back to a query you can check — I'll build one for your firm, free. **Start here → leadphoenixai.com/blog/deloitte-ai-finance-stack**