100 Best Claude KPI and Dashboard Prompts for Grocery Stores

Direct Answer

The best Claude prompts for KPI and dashboard for grocery stores are a curated set of actionable, department-aware prompts that enable fast, accurate KPI dashboards. They cover sales, inventory, promotions, labor, and vendor performance, and are designed to produce structured, dashboard-ready outputs that store teams can trust and act on.

Introduction

This page is a practical prompt library for KPI and dashboard tasks tailored to grocery stores. It is intended for retail analysts, store managers, and data teams seeking ready-to-run Claude prompts to build and monitor performance dashboards.

Each prompt in this list is crafted to be copyable, specific, and immediately usable without requiring readers to supply missing context.

How to Use These Claude Prompts

• Replace placeholders like [department], [store_id], and [date] with your actual data fields or dataset names.
• Add constraints such as time windows, thresholds, and data quality checks to tailor prompts to your environment.
• Request outputs in formats suitable for dashboards, such as JSON arrays or table-like JSON, and specify field names.
• Verify outputs by cross-checking a sample of the results with your source data before automating.

100 Best Claude KPI and Dashboard Prompts for Grocery Stores

1. Sales by department trend: You are an analytics assistant for a grocery chain. Task: generate a KPI dashboard snippet showing department-level sales trends over the last twelve weeks. Context: data source is a daily sales table with fields date, department, revenue, units_sold, store_id. Output format: JSON summary with lines for top department, bottom department, and a sparkline-friendly series. Constraints: exclude returns and voided transactions, aggregate by week, handle missing weeks by carrying forward last value.
2. Daily sales anomaly finder: Act as a store analytics analyst. Task: identify days with anomalous revenue compared to moving average over the past 28 days. Context: data_source = daily_sales with fields date, store_id, revenue, foot_traffic. Output format: bullet list of date, actual revenue, moving_average, percent_change, reason if available. Constraints: flag only days with percent_change beyond +/- 10%, exclude holidays unless flagged, provide tie-breaker notes.
3. Inventory turnover heatmap: Role: inventory analyst. Task: compute inventory turnover rate by department for the last 90 days and generate a heatmap-ready matrix. Context: data includes sku_id, department, stock_on_hand, sales_units_last_90, average_cost. Output: JSON matrix with department keys, turnover = (sales_units_last_90 / average_inventory). Constraints: handle zero stock gracefully, present per-store and total. Include interpretation notes.
4. Top promo impact drivers: Prompt to assess impact of promotions on weekly sales by department. Context: weekly_sales with fields week_start, department, promo_flag, revenue, units_sold, discount_rate. Output: ranked list of departments by delta revenue when promo_flag = true vs false. Constraints: show at least three weeks of data, include confidence notes if variance is high.
5. Stockout risk score: You are a risk analyst for grocery. Task: compute a stockout risk score per department for next 14 days using historical sell-through and stock levels. Context: fields include date, department, on_hand, sell_through_rate, lead_time_days. Output: JSON with department, risk_score (0-100), top contributing factor, recommended mitigation actions.
6. Vendor performance snapshot: Act as procurement analyst. Task: create a KPI snapshot comparing vendor_on_time_delivery, product_quality_issues, and fill_rate across vendors for the last quarter. Context: vendor_id, on_time_delivery_pct, quality_issues, fill_rate, spend. Output: table-like JSON with vendor_id and each KPI, include a ranking column.
7. Shelf space efficiency: Role: category manager. Task: calculate shelf_space_efficiency = revenue_per_sku / shelf_space_units by category for the current month. Context: data with category, sku_id, shelf_space_units, revenue, month. Output: JSON with category, avg_revenue_per_sku, avg_shelf_space, efficiency_score (0-1). Constraints: scale scores to 0-100 for dashboard display.
8. Promotions ROI map: You are a marketing analyst. Task: map promotions ROI by store and department over the last eight weeks. Context: data includes store_id, department, promo_id, discount_cost, revenue, units_sold. Output: list of promos with revenue_delta, ROI = (revenue - discount_cost) / discount_cost, and recommended next steps.
9. Customer basket analysis: Role: customer analytics lead. Task: produce a cross-sell matrix showing co-purchase likelihood between product categories for the last 30 days. Context: transactions with product_category, basket_id, product_id. Output: matrix with categories as rows and columns; fill with lift metric and sample size. Constraints: ignore returns, provide interpretation notes.
10. Forecast by department: Act as forecaster. Task: generate a 12-week forecast of department revenue with confidence intervals. Context: historical_department_revenue table with department, date, revenue. Output: JSON: department, forecast_12wk, lower_bound, upper_bound, methodology notes.
11. Labor cost vs sales: Role: operations analyst. Task: compare weekly labor_cost to weekly_sales by store to identify over- or under-staffing patterns. Context: fields store_id, week_start, labor_cost, revenue. Output: ranked list of stores with ratio and recommended actions.
12. Waste and spoilage tracker: You are an efficiency analyst. Task: track spoilage_cost and waste_percent by department for the last quarter. Context: data has department, spoilage_cost, waste_percent, date. Output: JSON with department, total_spoilage_cost, avg_waste_percent, hotspots.
13. Top selling SKUs: Role: merchandising analyst. Task: list top 20 SKUs by revenue in last 4 weeks, with department, stock_on_hand, and sell_through_rate. Output: JSON array of sku_id, revenue, department, stock_on_hand, sell_through_rate.
14. Returns impact dashboard: You are a returns analyst. Task: quantify impact of returns on net revenue per department over last 60 days. Context: fields department, returns_value, gross_revenue. Output: per-department table with net_revenue and return_rate.
15. Price elasticity check: Role: pricing analyst. Task: estimate price elasticity by department using historical price changes and demand signals. Context: data with department, price, units_sold, date. Output: elasticity_coefficient per department with interpretation guidelines.
16. Seasonal demand signal: Act as forecasts specialist. Task: identify seasonal patterns by department using last three years of weekly sales. Context: department, week_of_year, revenue. Output: seasonality_index per department and recommended adjustments.
17. Channel performance view: Role: channel analyst. Task: compare online vs in-store revenue and orders by department over the last six months. Context: channel, department, revenue, orders. Output: per-department delta and visualization-ready data.
18. Inventory aging report: You are an inventory analyst. Task: generate aging buckets for on_hand inventory by department for the last 30 days. Context: stock_on_hand, days_on_hand, department. Output: table with age_bucket, average_on_hand, turnover.
19. Markdown impact study: Role: promo analyst. Task: assess markdown impact on revenue and gross margin by department for last eight weeks. Context: discount_rate, revenue, gross_margin, department. Output: findings with recommended pricing actions.
20. Deal viability checker: Act as deal analyst. Task: evaluate potential wholesale deals by store and department using projected sales uplift and gross margin. Context: deal_id, expected_uplift, gross_margin, store_id, department. Output: recommendation and risk notes.
21. Basket size trend: You are a shopper insights analyst. Task: track average basket size by department and week for last 10 weeks. Context: basket_size = revenue/transactions. Output: time series with weekly_basket_size and momentum.
22. Promo leakage estimation: Role: promotions auditor. Task: estimate promo leakage as the share of promoted items bought without promotion in the last eight weeks. Context: items, is_promoted, is_discounted, quantity. Output: leakage_rate and action points.
23. Supplier stockout alerts: Role: procurement ops. Task: generate stockout alerts by SKU when on_hand falls below reorder_point within next 7 days. Context: sku_id, on_hand, reorder_point, lead_time_days. Output: alert list with suggested replenishment quantities.
24. Shelf space allocation: Act as space planner. Task: recommend shelf-space allocation changes by department to maximize revenue per square foot. Context: current_allocation, department, revenue_per_sqm, seasonal_adjustment. Output: suggested shifts with expected uplift and risk notes.
25. New product launch plan: Role: category manager. Task: build a launch dashboard for a new product with target cannibalization, forecast, and stock plan. Context: product_id, category, forecast_units, price, launch_date. Output: plan_summary and dashboard metrics.
26. Store benchmarking: You are a retail analyst. Task: create a benchmarking report comparing all stores on revenue per square foot, gross margin, and customer traffic for the last quarter. Output: per-store metrics with z-scores and highlights.
27. Traffic and conversion: Role: store performance analyst. Task: compute foot_traffic_to_sales_conversion_rate per store and day for the last 30 days. Output: dataset with store_id, date, conversion_rate. Constraints: exclude staff-only entrances if identifiable.
28. Profitability by department: Act as financial analyst. Task: calculate contribution margin per department and identify top and bottom performers for last month. Context: revenue, cogs, department. Output: table with margin, margin_percentage, and actions.
29. Waste reduction targets: Role: operations planner. Task: propose realistic waste reduction targets by department for next quarter. Context: baseline_waste, current_potential_reduction, department. Output: target_metrics and implementation steps.
30. Discount strategy simulator: You are a pricing engineer. Task: simulate three discount strategies for next four weeks and show impact on revenue, gross margin, and turns by department. Context: strategies, weekly_calendar, department. Output: comparison chart-ready data.
31. Inventory replenishment model: Role: supply chain analyst. Task: generate replenishment orders per store and department using EOQ-like logic with safety stock. Context: demand_forecast, lead_time, service_level. Output: orders_by_store_dept with quantities and dates.
32. Category health score: Act as category health auditor. Task: compute a health score per department using sell_through_rate, out_of_stock_rate, and markdown_rate. Output: table with score 0-100 and improvement actions.
33. Seasonal promo calendar: Role: promotions planner. Task: create a 12-week promotional calendar aligned to seasonality by department. Context: historical_promo, seasonal_index, department. Output: calendar with promo_id, date, expected impact.
34. Customer loyalty spikes: You are a loyalty analyst. Task: identify weeks with loyalty_points accumulation spikes and correlate to promotions. Context: loyalty_points, date, store_id, department. Output: list of spikes with attributed promo_id.
35. Pricing guardrails: Role: pricing strategist. Task: define minimum and maximum acceptable price floors and ceilings by product category based on elasticity and competitive data. Output: guardrail table with category, floor, ceiling, rationale.
36. Daily dashboard summary: Act as dashboard engineer. Task: generate a concise daily KPI snapshot for the grocery chain with key metrics across revenue, margin, turnover, and traffic. Output: JSON ready for widget card display.
37. Promotions overlap check: Role: promotions planner. Task: detect overlapping promotions by department and assess cumulative discount impact. Context: promo_schedule, department, discount_rate, cross_sell. Output: overlap_alerts with recommended sequencing.
38. New customer lift: You are a customer growth analyst. Task: estimate new customer acquisition lift from a loyalty campaign by week and store. Context: new_customers, campaign_id, store_id, week. Output: lift_values and attribution notes.
39. SKU rationalization plan: Role: merchandising strategist. Task: propose SKU cuts and consolidations by department to improve gross margin. Context: sku_list, revenue, cogs, average_inventory, department. Output: rationalization_action_list.
40. Unhealthy stock alert: Act as inventory control. Task: identify SKUs with high stock on hand but low sell_through_rate to avoid overstock. Context: sku_id, stock_on_hand, sell_through_rate. Output: alert list with recommended actions.
41. Cash flow sparkline: Role: finance analyst. Task: create cash flow sparkline by month for the last 12 months across all stores. Context: inflows, outflows, net_cash. Output: JSON sequence with month, net_cash.
42. Department growth forecast: You are a strategic planner. Task: forecast department revenue growth rate for next six quarters. Context: history_department_revenue, quarter, revenue. Output: growth_forecast per department and rationale.
43. Complaint sentiment signal: Role: customer experience analyst. Task: analyze feedback sentiment by department and flag negative signals with recommended actions. Context: feedback_id, department, sentiment_score. Output: department_signals with priority.
44. Eco-friendly initiative impact: Act as sustainability analyst. Task: measure impact of eco-friendly packaging on waste and costs by department. Context: packaging_type, waste_cost, revenue, department. Output: impact_report.
45. Delivery timeliness watch: Role: logistics analyst. Task: monitor delivery timeliness by store and supplier, flag late deliveries beyond threshold. Context: supplier_id, store_id, delivery_time, promised_time. Output: alerts with delay_reason.
46. New store viability: You are a market expansion analyst. Task: evaluate viability of a new store using projected revenue, population, competition, and setup_cost. Output: decision matrix with go/no-go recommendation.
47. Product mix optimizer: Role: category analyst. Task: optimize product mix by department to maximize revenue per SKU and reduce stockouts. Context: department, sku_id, revenue, stock. Output: recommended mix changes.
48. Discount leakage by store: You are a promotions auditor. Task: quantify discount leakage by store and department using historical promo data. Output: leakage_report with store_id, department, leakage_rate.
49. Best sellers by week: Role: sales analyst. Task: list weekly top-selling SKUs by revenue with department and stock_on_hand. Output: array of sku_id, revenue, department, stock_on_hand.
50. Inventory safety stock plan: Act as supply planner. Task: calculate safety stock per SKU using demand variability and service level 95 percent. Output: sku_id, safety_stock, rationale.
51. Store heat map: Role: analytics lead. Task: generate a store-level heat map of revenue per square foot by department. Context: store_id, department, revenue_per_sqm. Output: grid-ready data.
52. Lead time optimization: You are a supply chain engineer. Task: identify opportunities to reduce supplier lead time by days and regions. Output: list of actions with expected impact.
53. Markdown strategy test: Role: pricing analyst. Task: test two markdown strategies in parallel and compare gross margin impact by department over four weeks. Output: results with recommended strategy.
54. Cost-to-serve view: Act as cost analytics lead. Task: compute cost-to-serve per department including logistics, packaging, and handling. Output: table with total_cost and cost_per_unit.
55. Deal performance log: Role: vendor manager. Task: log and summarize the performance of wholesale deals by promo_period and store. Output: deal_id, uplift, margin, store_ids.
56. Calendar anomaly detection: You are a data quality auditor. Task: detect gaps or duplicates in daily sales calendar and propose fixes. Output: list of anomalies with recommended corrections.
57. Customer segment insights: Role: customer analytics lead. Task: segment customers by basket size and frequency; summarize key behaviors by segment for last quarter. Output: segments with actions.
58. Promotion cadence plan: Act as promotions planner. Task: design a cadence of promotions to balance revenue and margins for next 12 weeks. Output: calendar with cadence rules.
59. SKU price ladder: Role: pricing analyst. Task: build a price ladder for a set of SKUs to optimize margin with competitive pricing provided. Output: per-SKU ladder with floors and ceilings.
60. Turnover by store: You are an operations analyst. Task: compute product turnover by store and department for the last quarter. Output: table with store_id, department, turnover, turnover_rank.
61. Lunch hour sales spike: Role: category planner. Task: identify sales spikes around lunch hours by department and time of day. Output: list of time_buckets with uplift and recommended actions.
62. Seasonal staffing plan: Act as labor planner. Task: create staffing plan aligned to seasonal demand by store. Output: shift plan with headcount and coverage notes.
63. Delivery route efficiency: You are a logistics analyst. Task: optimize delivery routes to reduce fuel cost per store. Output: route_changes with expected savings.
64. Loyalty redemption impact: Role: loyalty program analyst. Task: measure impact of loyalty redemptions on basket size and revenue. Output: correlation data and recommendations.
65. Product availability score: Act as product availability specialist. Task: score product availability by department using on_hand and sell_through. Output: availability_score 0-100 with remedial actions.
66. Weekend sales uplift: Role: merchandising analyst. Task: quantify weekend uplift by department and store. Output: table with uplift_percent and confidence.
67. Basket heatmap by time: You are a shopper insights analyst. Task: create a time-based heatmap of basket size by hour and department. Output: grid-ready data with hour_bins.
68. Inventory carrying cost: Role: finance analyst. Task: calculate carrying cost per SKU based on holding cost rate and average_inventory. Output: table with carrying_cost_per_unit.
69. Cross-dock efficiency: Act as supply chain ops. Task: evaluate cross-dock efficiency by supplier and store. Output: score and improvement actions.
70. Price change risk: You are a risk-aware pricing analyst. Task: assess risk of price changes on demand using historical elasticity data. Output: risk_score per department with mitigation steps.
71. New aisle placement: Role: space planner. Task: simulate new aisle placement by department to maximize shopper exposure. Output: suggested placements and expected lift.
72. Out-of-stock forecast: You are an inventory forecaster. Task: predict OOS risk by SKU for the next 14 days. Context: on_hand, lead_time, demand_history. Output: list of SKUs with risk_score.
73. Promotional cadence by week: Role: promotions planni and datasource. Task: generate weekly promo cadence aligned to events and inventory. Output: calendar with promo_id and week.
74. SKU profitability: Act as profitability analyst. Task: calculate gross margin per SKU and identify low-margin items by department. Output: list of sku_id with margin and recommended action.
75. Store-level KPI dashboard: Role: dashboard engineer. Task: design a store-level KPI dashboard schema including revenue, margin, traffic, and inventory. Output: metric definitions and calculation logic.
76. Forecast accuracy check: You are a forecasting quality expert. Task: compute forecast accuracy by department over last six months and propose improvements. Output: accuracy_metrics by department.
77. Supplier risk score: Role: procurement risk analyst. Task: rate suppliers on risk factors and resilience. Output: supplier_id, risk_score, mitigation steps.
78. Promotions cross-sell: Act as promotions strategist. Task: design cross-sell bundles for promotions to boost average order value. Context: basket, departments, promo_id. Output: bundle_suggestions.
79. Markdown reset plan: You are a pricing operations lead. Task: plan a markdown reset after a promotion season with targets for margin and sell-through. Output: plan with milestones.
80. New product scorecard: Role: product manager. Task: score a new product against criteria: demand, margin, fit, and shelf life. Output: scorecard with recommended go/no-go.
81. Sales funnel health: Act as funnel analyst. Task: measure drop-off at each stage of the shopper journey with store data. Output: funnel steps and improvement ideas.
82. Gross margin by category: Role: financial analyst. Task: compute gross margin by category for last month and identify anomalies. Output: category_margin table.
83. Returns pattern map: You are a returns analyst. Task: map returns by department to identify patterns and policy adjustments. Output: heatmap-ready data.
84. Promotions payout cycle: Role: promotions manager. Task: outline payout cycle for promotions including timing, approvals, and accounting entries. Output: process steps.
85. Demand signal integration: Act as data integrator. Task: fuse external demand signals (events, weather) with internal sales history for forecasting by department. Output: integrated_forecast data.
86. Asset utilization: You are a store operations analyst. Task: measure asset utilization by department including fixtures and equipment. Output: utilization_score and recommendations.
87. Coupon stack analysis: Role: promotions auditor. Task: analyze stacking of coupons and its impact on revenue and margins. Output: stacking_insights with policy recommendations.
88. Branch comparison: You are a regional analyst. Task: compare branches on revenue per customer, basket size, and traffic growth. Output: branch_comparison table.
89. Checkout queue length: Role: store operations manager. Task: analyze average checkout queue length by hour and propose staffing adjustments. Output: schedule recommendations.
90. Sustainability KPI: Act as sustainability data analyst. Task: track energy use, waste, and packaging metrics across stores. Output: sustainability_kpi dashboard data.
91. Compliance checklist: Role: compliance analyst. Task: generate a KPI compliance checklist for store operations and promotions. Output: checklist with pass/fail and remediation.
92. Store roll-out readiness: You are a new-store rollout analyst. Task: evaluate readiness of a new store including inventory, staffing, and systems. Output: readiness_score and action plan.
93. Eco-promo scoring: Role: marketing analyst. Task: score eco-friendly promotions on uptake and waste impact. Output: eco_promo_score with notes.
94. Data quality health: Act as data quality engineer. Task: assess data quality across sales, inventory, and promotions datasets. Output: quality_score and remediation plan.
95. Customer feedback loop: You are a CX analyst. Task: design a feedback loop from store to dashboard to close the loop on issues. Output: process diagram steps.
96. Cash register anomalies: Role: audit analyst. Task: detect cash register anomalies by store and hour. Output: anomaly_list with suggested investigations.
97. Affiliates impact view: Act as partner analytics. Task: measure impact of affiliate channels on store sales by department. Output: attribution_table.
98. Forecast uncertainty plan: Role: forecasting lead. Task: outline plan to quantify and communicate forecast uncertainty to executives. Output: plan with metrics.
99. Operational health score: You are a store ops analyst. Task: create an overall operational health score combining uptime, stock, and service metrics. Output: scorecard with drivers.
100. Executive KPI digest: Role: executive reporting. Task: generate a concise executive digest of KPI highlights by department for the month. Output: overview with top and bottom performers.

Best Practices

• Use consistent field naming across prompts to simplify integration with your dashboard backend.
• Test prompts with a small data slice to validate output structure and logic before scaling to all stores.
• Combine related prompts into a dashboard panel for cohesive insights and easier monitoring.
• Document assumptions and data sources alongside the prompt outputs for auditability.
• Regularly update prompts to reflect seasonality, promotions, and supply chain changes.

Common Mistakes to Avoid

• Using vague labels or generic goals that make outputs non-actionable.
• Overfitting prompts to a single store or scenario, reducing generalizability.
• Ignoring data quality and missing values, which leads to misleading results.
• Forgetting to specify output formats or field names, causing integration friction.
• Neglecting to include safety checks for negative values, outliers, or data gaps.

FAQ

What is KPI and dashboard prompting for grocery stores best used for?

It is used to generate structured, ready-to-display analytics focused on sales, inventory, promotions, and store performance to inform decisions.

How should I adapt prompts to my data schema?

Replace placeholders with your actual field names and dataset identifiers, and specify aggregation rules that match your data warehouse.

Can prompts handle multiple stores at once?

Yes, prompts can include store_id filters and return per-store metrics plus a total across all stores.

What output format works best for dashboards?

JSON objects and arrays that map cleanly to widgets, tables, and charts, with standardized field names.

How do I ensure data quality in outputs?

Include constraints, validation steps, and cross-check samples against source data before automating the prompts.

Are these prompts suitable for executives?

Yes, use the executive digest prompt to summarize top and bottom performers and key trends.