Operations Prompts to Understand Your Business Better

You are a revenue operations manager auditing the go-to-market technology stack. Tech stack data: [PASTE: Tool | Category | Users | Annual cost | Integration to CRM (yes/no) | Usage rate (high/medium/low) | Owner | Last evaluated] Audit for: 1. Duplication — tools doing the same job; consolidation opportunity 2. Unused tools — licenses paid for with low adoption; assess value vs. cost 3. Integration gaps — tools not connected to CRM creating manual data entry or blind spots 4. Critical dependencies — tools the business cannot function without; ensure contract continuity 5. Cost optimization — tools that could be replaced by CRM-native features without losing capability Output: Tech stack audit. Consolidation opportunities with estimated savings. Integration gap list. Tools to retire. Tools to protect. Annual savings from recommended changes.

You are a CRM administrator auditing the CRM field configuration for relevance and data quality. CRM data: [PASTE: Object (Account/Contact/Deal/Lead) | Field name | Field type | % populated (from CRM report) | Last used in a report or automation | Created date | Business purpose (known or unknown)] Audit for: 1. Unused fields — fields with <20% population and no use in reports/automations; candidates for removal 2. Duplicate fields — multiple fields capturing the same data (e.g., three different "industry" fields) 3. Fields without a clear owner — who is responsible for keeping this data accurate? 4. Required fields not being completed — fields critical for reporting but consistently blank 5. Field naming confusion — fields with unclear names that reps interpret differently Output: Field audit report. Remove / consolidate / rename / make required — recommendation for each flagged field. Total field count reduction available. Estimated data quality improvement.

You are a financial reporting manager preparing the monthly balance sheet review. Balance sheet data: [PASTE: Account | Current balance | Prior month balance] Known events this period: [DESCRIBE: New contracts, debt draws, acquisitions, large purchases — or write "none"] Materiality threshold: $[AMOUNT] For each line above materiality: - Calculate $ change and % change - Write a 2-sentence plain-English explanation of what drove the change - Flag any movement that cannot be explained by known events — needs investigation before finalizing Output: Flux table with narrative notes grouped by Current Assets / Non-Current Assets / Liabilities / Equity. End with: movements consistent with business activity OR list items requiring additional review.

You are a finance process analyst reviewing the close process for improvement opportunities. Current close process: [DESCRIBE: Each close step — who does what, how long it takes, what tool they use, known pain points] Example format: - Step 1: GL cutoff (Day 0, 2 hours, manual, error-prone) - Step 2: Reconcile balance sheet accounts (Days 1–3, 8 hours, spreadsheet-based) - Step 3: Variance explanations (Day 4, 3 hours, drafted in Word) For each step, recommend: - Automation opportunity (AI, RPA, ERP native feature, or third-party tool) - Estimated time saved per period - Implementation complexity (low/medium/high) - Required controls to maintain if automated Prioritize: Highest time savings + lowest implementation complexity. Output: Improvement roadmap table. Add a summary: current total close time vs. target close time with recommended changes.

You are a controller reviewing accounts payable. AP aging data: [PASTE: Vendor | Invoice # | Invoice date | Amount | Due date | Aging bucket (Current/1-30/31-60/61-90/90+)] Current cash balance: $[AMOUNT] Produce: 1) Aging summary — total payables by bucket with % of total 2) Top 10 vendors by outstanding balance — flag any with invoices 60+ days overdue 3) Duplicate invoice check — same vendor + same amount ±5% + dates within 7 days 4) Cash exposure — payables due in next 14 days vs. current cash balance 5) Vendor risk flags — vendors with past-due payables AND open purchase orders Output: Executive memo. End with 3 highest-priority actions this week. Tone: Direct, no filler.

You are a procurement analyst reviewing vendor spend for [PERIOD]. Spend data: [PASTE: Vendor | Category | Invoice total | Number of invoices | Department | Payment terms] Analyze: 1) Total spend by vendor — top 10 by amount 2) Spend by category — flag any category where spend increased >20% vs. prior period 3) Department spend breakdown — which departments are driving the largest payables? 4) Payment terms compliance — vendors where average days to pay exceeds agreed terms 5) Consolidation opportunities — categories with 3+ vendors where spend could be rationalized Output: Spend analysis report. Top 3 recommendations for cost reduction or process improvement.

You are a treasury manager preparing the daily cash position. Bank account data: [PASTE: Bank | Account | Opening balance | Deposits today | Payments today | Closing balance | Available credit line] Also note: [PASTE: Outstanding checks not yet cleared | Payroll funding requirements this week | Large payments due in next 7 days] Produce: 1) Consolidated cash position by account and total 2) Liquidity summary — available cash + undrawn credit line 3) Near-term cash requirements — payments and funding needs in next 7 days 4) Cash concentration recommendations — accounts to sweep or fund 5) Minimum balance check — flag any account below operating minimum of $[AMOUNT] Output: One-page treasury report suitable for CFO morning briefing.

You are an AR analyst preparing the monthly DSO analysis. Monthly data for the past 6 months: [PASTE: Month | Total AR | Monthly revenue | AR by aging bucket (Current/30/60/90/90+)] Calculate for each month: 1) DSO = (AR balance / Revenue) × days in period 2) Best-possible DSO = (Current AR / Revenue) × days in period 3) Delinquency ratio = (AR over 30 days / Total AR) 4) Collection effectiveness index (CEI) Identify: - Month-over-month trend — improving or deteriorating - Seasonal patterns - If DSO increased: which aging bucket drove it? - Benchmark: how does current DSO compare to net payment terms? Output: 6-month trend table + narrative analysis. End with: DSO is improving/deteriorating because [specific reason], and the single most impactful action to improve it.

You are a credit analyst reviewing customer payment behavior. Payment history: [PASTE: Customer | Invoice date | Invoice amount | Due date | Payment date | Days early/late | Discount taken?] For each customer, analyze: 1) Average days to pay vs. stated terms 2) Payment consistency — does behavior vary by invoice size or time of year? 3) Discount behavior — taking discounts they're not entitled to? 4) Deduction behavior — paying short without explanation? 5) Trend — improving or deteriorating over the last 6 months? Segment customers into: Excellent payer / Acceptable payer / At-risk / Problem account. For At-risk and Problem accounts: recommend specific credit management action. Output: Customer payment scorecard table + recommended actions for At-risk and Problem accounts.

You are an FP&A analyst reconciling the difference between recognized revenue and cash collected. Data: [PASTE: Revenue recognized this period | Cash collected this period | Beginning AR balance | Ending AR balance | Deferred revenue movement | Any write-offs] Produce a revenue-to-cash bridge: Revenue recognized + Beginning AR − Ending AR − Write-offs ± Deferred revenue change = Cash collected Explain any variance between the bridge calculation and actual cash collected. Flag: AR increasing faster than revenue (collection problem) / Deferred revenue increasing significantly (billing ahead of delivery). Output: Bridge table with narrative explanation. End with: the primary driver of the gap between revenue and cash this period is [specific explanation].

You are an FP&A analyst preparing the monthly budget variance report. Variance data: [PASTE: Department | Budget | Actual | Variance $ | Variance % | GL account or cost category] Produce: 1) Variance summary — each department's total budget, actual, variance ($), variance (%). Sort by largest overage first. 2) Deep dive on overages — for any department more than $[THRESHOLD] or [%] over budget: break down the top 3 GL accounts driving the overage. For each: budgeted amount, actual, variance, plain-English explanation of what likely caused it. 3) Favorable variances — departments under budget >10%. Flag any that look like delayed spend rather than genuine savings. 4) Trend context — compare this period's variances to the prior two periods. Are the same departments consistently over/under? 5) Forecast impact — based on current run rate, project full-year spend vs. annual budget for the top 5 overspending departments. Output: Board-ready variance report. Use tables, not paragraphs. End with 3 recommendations for the CFO.

You are a senior FP&A analyst updating the full-year financial forecast. Actuals to date: [PASTE: Month | Revenue actual | Revenue budget | Expense actual | Expense budget — for each completed month] Remaining months: [DESCRIBE: Any known changes to revenue drivers, headcount plans, major expenses, one-time items expected in H2] Update the full-year forecast: 1) Revenue: reforecast remaining months using current run rate + known adjustments; compare to budget 2) Expenses: reforecast by major category using actuals trend + known changes 3) EBITDA bridge: original budget → reforecast, showing drivers of the change 4) Scenarios: base case (current trajectory) / upside (best case, describe assumptions) / downside (risk case, describe assumptions) 5) Key assumptions: list the top 3 variables that would most change the forecast Output: Reforecast summary table + EBITDA bridge + scenario comparison. CFO should be able to take this to the board.

You are a treasury analyst reviewing forecast accuracy. Data: [PASTE: Week | Forecasted cash in | Actual cash in | Forecasted cash out | Actual cash out | Forecasted ending cash | Actual ending cash — for last 8 weeks] Analyze: 1) Forecast accuracy — average variance between forecasted and actual cash in/out ($ and %) 2) Systematic biases — do we consistently over- or underforecast cash in? Cash out? 3) Largest single-week misses — what caused them? 4) Impact on liquidity planning — did any misses cause us to come close to minimum cash threshold? 5) Recommendations to improve forecast accuracy — specific data sources or process changes Output: Forecast accuracy report with trend chart description. End with: the #1 change that would most improve our cash forecast accuracy.

You are a supply chain analyst reviewing inventory health. Inventory data: [PASTE: SKU | Description | Category | On-hand quantity | Unit cost | Extended value | Last sale date | Average monthly demand | Lead time (days)] Produce: 1) ABC classification — A items (top 80% of value), B items (next 15%), C items (bottom 5%) 2) Dead stock — items with no sales in 6+ months; show quantity and extended value 3) Slow-moving stock — items with <50% of normal monthly demand sold in last 3 months 4) Excess stock — items where on-hand > [X months] of average demand 5) Stockout risk — items where on-hand < safety stock or reorder point Output: Inventory health dashboard. Total excess and dead stock value. Top 10 items to action immediately.

You are a demand planner reviewing forecast accuracy for the period. Forecast vs. actual data: [PASTE: SKU | Forecasted demand | Actual demand | Variance units | Variance % | Category] Analyze: 1) Overall forecast accuracy (MAPE — mean absolute percentage error) for the period 2) Best-performing categories — lowest forecast error 3) Worst-performing categories — highest forecast error; what drove the miss? 4) Bias check — are we consistently over-forecasting or under-forecasting certain categories? 5) SKUs with >50% forecast error — identify and flag for manual review in next cycle Output: Forecast accuracy report. End with: top 3 actions to improve forecast accuracy next period (be specific — not just "improve the model").

You are a supply chain manager assessing supplier risk. Supplier data: [PASTE: Supplier | Category | Annual spend | % of total spend in category | Lead time | On-time delivery % (last 6 months) | Single-source? (yes/no) | Country of origin | Quality rejection rate] Assess each supplier on: 1) Dependency risk — what % of our total spend does this supplier represent? Single source? 2) Performance risk — delivery reliability and quality issues 3) Geographic concentration — suppliers clustered in same region or country 4) Financial risk — any signals of supplier financial stress (if known) 5) Disruption scenario — if this supplier went down for 30 days, what is the operational and revenue impact? Output: Supplier risk matrix — risk level (High/Medium/Low) for each, with key risk driver and recommended mitigation (backup supplier, dual-source, safety stock buffer, contract clause).

You are an inventory manager performing ABC/XYZ analysis for planning policy decisions. Inventory data: [PASTE: SKU | Annual revenue (or usage value) | Annual demand quantity | Demand variability (coefficient of variation if known, or describe as stable/variable/highly variable)] ABC classification (by annual value): - A items: top 80% of total value - B items: next 15% - C items: bottom 5% XYZ classification (by demand variability): - X items: stable demand (CV < 0.5) - Y items: variable demand (CV 0.5–1.0) - Z items: highly variable or irregular demand (CV > 1.0) For each resulting segment (AX, AY, AZ, BX, BY, BZ, CX, CY, CZ): - Recommended forecasting method - Recommended replenishment policy (MRP / reorder point / kanban / manual review) - Safety stock approach Output: Segmentation matrix with policy recommendations. Count and value of items in each segment.

You are a procurement manager evaluating VMI with a key supplier. Current state data: [PASTE: Supplier | Items managed | Current ordering frequency | Average inventory value | Stockout incidents last 12 months | Current PO processing cost per order] Build a VMI proposal assessing: 1) Inventory reduction potential — estimated % reduction in safety stock if supplier manages replenishment 2) Stockout improvement — expected reduction in stockouts 3) Administrative savings — PO processing costs eliminated 4) Supplier requirements — what system access, data sharing, and performance guarantees are needed 5) Risk considerations — what happens if supplier performance deteriorates under VMI? Output: VMI business case — current state costs vs. VMI costs. Go/no-go recommendation with conditions.