35 ChatGPT-5.5 Prompts for Supply Chain Managers: Demand Forecasting, Inventory Optimization, Logistics Planning, and Vendor Risk Assessment

This article contains 35 production-ready ChatGPT-5.5 prompts tailored for supply chain managers. Each prompt is copy-paste ready, includes variables you can customize, and is accompanied by a brief explanation and suggested output format. Use these prompts to accelerate demand forecasting, optimize inventory, plan logistics, assess vendor risk, and develop strategic supply chain initiatives.

Introduction & How to Use These Prompts

These prompts are designed for ChatGPT-5.5 and assume the model has access to relevant data you provide in the prompt (CSV, JSON, or pasted tables). For best results:

• Provide clean historical data when requested—use CSV or JSON as the variable placeholders suggest.
• Customize variables (e.g., {{PRODUCT_SKU}}, {{REGION}}, {{TIME_WINDOW}}) before pasting into ChatGPT-5.5.
• Ask the model to return structured outputs (JSON or CSV) for easy ingestion into downstream tools.

Where applicable, the prompts request confidence intervals, assumptions, and practical actions so outputs are decision-ready. You can chain prompts—for example, feed a cleaned forecast into an inventory optimization prompt.

Related resources:

Supply chain professionals who also manage research-intensive procurement decisions will find complementary prompts in our collection for academic researchers. The 40 ChatGPT-5.5 prompts for literature reviews, hypothesis generation, and data interpretation can be adapted for supplier evaluation research and market analysis. 40 ChatGPT-5.5 Prompts for Academic Researchers.

,

Supply chain teams that collaborate with product design departments can leverage our 40 ChatGPT-5.5 prompts for UX designers. The user journey mapping and usability testing prompts translate directly to customer experience optimization in logistics and fulfillment workflows. 40 ChatGPT-5.5 Prompts for UX Designers.

Section 1 — Demand Forecasting

Seven prompts focused on seasonal analysis, trend prediction, and demand sensing. Each prompt asks ChatGPT-5.5 for analytical steps and structured outputs you can use directly.

You are ChatGPT-5.5, an advanced supply chain forecasting assistant. Given historical sales data in CSV format, perform a seasonal decomposition and return seasonal indices for the requested seasonality. Input variables:
- {{SALES_HISTORY_CSV}} : CSV with columns [date, product_sku, units, region]
- {{PRODUCT_SKU}} : target SKU (e.g., "SKU-12345")
- {{START_DATE}} : start date for analysis (YYYY-MM-DD)
- {{END_DATE}} : end date for analysis (YYYY-MM-DD)
- {{SEASONAL_PERIOD}} : integer seasonal period in data points (e.g., 12 for monthly seasonality)

Task:
1. Load and filter data for {{PRODUCT_SKU}} and date range.
2. If necessary, aggregate to the time frequency implied by {{SEASONAL_PERIOD}} (e.g., monthly).
3. Perform additive and multiplicative decomposition; choose the best-fit method with justification.
4. Output:
   - "method": "additive" or "multiplicative"
   - "seasonal_indices": list of seasonal indices ordered by period (length = {{SEASONAL_PERIOD}})
   - "trend_series_sample": first 6 trend values sample
   - "residual_stats": {mean, std, autocorrelation_lag1}
   - "recommendation": 2-3 actions to apply seasonal index in planning

Return output as JSON only.

You are ChatGPT-5.5. Using the filtered time series provided, produce a 12-month trend projection with 80% and 95% confidence intervals. Inputs:
- {{TIME_SERIES_CSV}} : CSV with [date, value] for aggregated demand (filtered externally)
- {{FORECAST_HORIZON_MONTHS}} : integer (e.g., 12)
- {{MODEL_PREFERENCE}} : "auto", "ARIMA", "ETS", or "Prophet"

Task:
1. Describe which model you'll use and why (if "auto", compare at least two models quickly).
2. Fit the model and produce point forecast and 80/95% CI for each month of the horizon.
3. Provide performance metrics on backtest (MAE, RMSE, MAPE).
4. Output JSON with keys: "model", "params_summary", "backtest_metrics", "forecasts": [{date, point, ci80_low, ci80_high, ci95_low, ci95_high}], and "assumptions".

Return JSON only; include short notes for potential anomalies affecting confidence intervals.

You are ChatGPT-5.5. Perform demand sensing using near-real-time indicators. Inputs:
- {{RECENT_SALES_CSV}} : last 30-90 days CSV [date, product_sku, units, channel]
- {{NON_SALES_INDICATORS_JSON}} : JSON object with keys like {"search_trends": [date,value], "web_visits": [...], "promotions": [...]} aligned by date
- {{PRODUCT_SKU}} : SKU to analyze
- {{TIME_WINDOW_DAYS}} : integer to define sensing window (e.g., 14)

Task:
1. Align and normalize indicators with recent sales for {{PRODUCT_SKU}}.
2. Use weighted regression or similarity matching to detect demand shifts compared to the previous comparable period.
3. Output:
   - "demand_change_percent": estimated short-term uplift/drop percent (relative to prior period)
   - "signal_strength": {"low","medium","high"} with numeric score 0-1
   - "drivers": ranked list of top 3 indicators contributing to change
   - "recommended_actions": 3 operational actions (e.g., adjust replenishment, review promotions)

Return JSON and include a short explanation (2-3 sentences) of how you weighted signals.

You are ChatGPT-5.5. Estimate promotional uplift and cannibalization for a given promotion period. Inputs:
- {{HISTORICAL_SALES_CSV}} : CSV [date, product_sku, units, price, promo_flag]
- {{PROMO_PERIOD_START}} : YYYY-MM-DD
- {{PROMO_PERIOD_END}} : YYYY-MM-DD
- {{TREATED_SKUS}} : list of SKUs on promotion
- {{CONTROL_SKUS}} : list of comparable SKUs not promoted (optional)

Task:
1. Use difference-in-differences or time-series causal impact to estimate uplift vs. baseline.
2. Estimate cannibalization on related SKUs and any post-promo dips.
3. Output:
   - "uplift_absolute": total incremental units and revenue
   - "uplift_percent": percent lift vs baseline
   - "cannibalization_percent": estimated percent of uplift taken from other SKUs
   - "post_promo_effect": expected drop (if any)
   - "recommendation": 3 suggestions to improve promo ROI

Return JSON with numeric fields and a brief notes section describing methods used.

You are ChatGPT-5.5. Produce a demand ramp forecast for a newly launched product using analog SKUs and launch assumptions. Inputs:
- {{ANALOG_SKUS_DATA_CSV}} : CSV with historical launches for analogous SKUs [days_since_launch, units, marketing_spend_level, distribution_points]
- {{NEW_PRODUCT_LAUNCH_PARAMS}} : JSON {expected_marketing_spend_level, initial_distribution_points, price, promo_plan}
- {{FORECAST_HORIZON_DAYS}} : integer (e.g., 180)

Task:
1. Identify typical ramp shapes from analog SKUs and cluster templates (fast ramp, slow ramp, plateau).
2. Match the new product's launch params to analog templates and produce three scenarios: conservative, baseline, optimistic.
3. Output:
   - "scenarios": [{name, daily_forecast: [{date, units}], cumulative_units_at_30_60_90}, ...]
   - "assumptions": key drivers and sensitivity analysis (±10% marketing, ±20% distribution)
   - "recommended_milestones": 3 checkpoints for go/no-go

Return JSON. Provide short guidance on what additional data would improve forecast accuracy.

You are ChatGPT-5.5. Detect anomalies in demand and propose root causes. Inputs:
- {{DEMAND_SERIES_CSV}} : CSV [date, product_sku, units]
- {{WINDOW_DAYS}} : integer (e.g., 90) to define baseline window
- {{EXTERNAL_EVENTS_JSON}} : JSON with events {date, event_type, description} (optional)
- {{PRODUCT_SKU}} : SKU to analyze

Task:
1. Flag significant positive/negative anomalies vs. baseline.
2. For each anomaly, assess probable causes (promotions, stockouts, season, marketing, external events).
3. Return a JSON array: [{date_or_period, anomaly_type, magnitude_percent, probable_causes_ranked, confidence_score (0-1), recommended_actions}].

Include a short summary (2-4 sentences) describing the top 3 anomalies and next investigative steps.

You are ChatGPT-5.5. Provide a hierarchical forecast for multiple SKUs with reconciliation to higher-level aggregates. Inputs:
- {{MULTI_PRODUCT_CSV}} : CSV [date, product_sku, region, units]
- {{HIERARCHY_DEFINITION_JSON}} : JSON describing aggregation levels (e.g., {"level1":"global", "level2":["region"], "level3":["product_category","product_sku"]})
- {{FORECAST_HORIZON_DAYS}} : integer

Task:
1. Produce independent SKU-level forecasts using an appropriate model.
2. Reconcile forecasts so aggregates at each hierarchy level equal sum of children (top-down or bottom-up reconciled; choose best and explain).
3. Output JSON: {"forecasts": [{"product_sku","region","date","point_forecast"}], "reconciliation_method", "summary_metrics_by_level": [{"level", "MAE", "RMSE"}]}

Also provide two quick visualizations suggestions to validate reconciliation.

Section 2 — Inventory Optimization

Seven prompts focused on safety stock, reorder points, ABC analysis, and multi-echelon inventory tactics.

You are ChatGPT-5.5. Calculate safety stock and reorder point for one SKU given demand variability and lead time. Inputs:
- {{DEMAND_HISTORY_CSV}} : CSV [date, units] for the SKU
- {{LEAD_TIME_DAYS}} : average supplier lead time in days
- {{LEAD_TIME_STD_DAYS}} : standard deviation of lead time in days (optional)
- {{SERVICE_LEVEL}} : desired fill-rate/service level as percent (e.g., 95)
- {{REPLENISHMENT_POLICY}} : "continuous_review" or "periodic_review"

Task:
1. Compute average daily demand and demand STD over an appropriate window (specify the window you used).
2. Calculate safety stock using appropriate formula for continuous review with stochastic lead time.
3. Provide reorder point and suggested order quantity (EOQ if no batch constraints).
4. Output JSON: {"average_daily_demand", "demand_std", "safety_stock_units", "reorder_point_units", "suggested_order_quantity", "assumptions"}

Include 2 practical notes for implementing in ERP (e.g., rounding, review frequency).

You are ChatGPT-5.5. Calculate per-warehouse reorder points for a SKU across a distribution network. Inputs:
- {{DEMAND_BY_DC_CSV}} : CSV [date, warehouse_id, units]
- {{LEAD_TIME_BY_SUPPLIER_JSON}} : JSON {warehouse_id: lead_time_days}
- {{SAFETY_STOCK_POLICY}} : "centralized" or "local" (defines whether safety stock is pooled centrally or per warehouse)
- {{SERVICE_LEVEL}} : percent

Task:
1. Estimate demand and variability per warehouse.
2. If SAFETY_STOCK_POLICY == "centralized", compute pooled safety stock and allocation per warehouse using proportional demand or square-root pooling; explain choice.
3. Output JSON: [{"warehouse_id","average_daily_demand","safety_stock","reorder_point","recommended_reorder_qty"}]

Add guidance on transfer policies and when to rebalance inventory between warehouses.

You are ChatGPT-5.5. Perform an ABC (value) and XYZ (demand variability) classification for a product catalog. Inputs:
- {{PRODUCT_SALES_CSV}} : CSV [product_sku, units_sold_value_period, units_sold_count_period]
- {{CLASSIFICATION_PERIOD_DAYS}} : integer (e.g., 365)

Task:
1. Compute annual revenue contribution per SKU and rank for ABC classification: A (top 70% value), B (next 20%), C (last 10%) by default—explain thresholds used.
2. Compute demand variability (coefficient of variation) to assign XYZ classes: X low variability, Y medium, Z high.
3. Output JSON: [{"product_sku","abc_class","xyz_class","annual_revenue","coefficient_of_variation","recommended_policy"}]
4. Provide a short policy matrix mapping ABC/XYZ to inventory tactics (e.g., safety stock multiples, review frequency).

Return JSON and a short paragraph explaining how to adjust thresholds for your business.

You are ChatGPT-5.5. Compute EOQ considering batch sizes, minimum order quantities, and multiple cost components. Inputs:
- {{ANNUAL_DEMAND_UNITS}} : integer
- {{ORDER_COST_PER_ORDER}} : fixed cost per order (USD)
- {{HOLDING_COST_PER_UNIT_PER_YEAR}} : cost (USD)
- {{UNIT_COST}} : purchase price per unit (USD)
- {{MIN_ORDER_QTY}} : integer (minimum order quantity)
- {{MULTIPLE_ORDER_LOT}} : integer (e.g., must order in multiples of 10) optional

Task:
1. Compute unconstrained EOQ with classic formula.
2. Apply constraints: round up to nearest multiple of {{MULTIPLE_ORDER_LOT}} and at least {{MIN_ORDER_QTY}}.
3. Report total annual cost under unconstrained and constrained EOQ and percent difference.
4. Output JSON: {"eoq_unconstrained","eoq_constrained","annual_cost_unconstrained","annual_cost_constrained","percent_increase_due_to_constraints","assumptions"}

Provide a short recommendation whether to negotiate MOQs to reduce total cost.

You are ChatGPT-5.5. Generate a prioritized set of inventory health KPIs and compute them from provided datasets. Inputs:
- {{INVENTORY_ON_HAND_CSV}} : CSV [date, warehouse, product_sku, on_hand_qty]
- {{SALES_HISTORY_CSV}} : CSV [date, product_sku, units_sold]
- {{SLOW_MOVING_DAYS_THRESHOLD}} : integer (e.g., 180)

Task:
1. Compute KPIs: days of inventory (DOI), turnover rate, days of supply, percentage of obsolete inventory (no sales in last {{SLOW_MOVING_DAYS_THRESHOLD}} days), stockout rate (if stockout events provided or infer from zero inventory with positive demand).
2. Rank top 10 SKUs by risk (high DOI + low turnover).
3. Output JSON: {"kpis": {...}, "top_at_risk": [{"product_sku","metric","value"}], "suggested_actions": 5}

Give short visualization suggestions for a dashboard (3 charts).

You are ChatGPT-5.5. Design a multi-echelon inventory strategy for a two-level network (central DC and regional DCs). Inputs:
- {{DEMAND_BY_REGION_CSV}} : CSV [date, region, product_sku, units]
- {{LEAD_TIME_CENTER_TO_REGION_DAYS}} : integer or JSON by region
- {{LEAD_TIME_SUPPLIER_TO_CENTER_DAYS}} : integer
- {{SERVICE_LEVELS}} : JSON {central: percent, regional: percent} or single percent

Task:
1. Recommend whether to pool safety stock centrally or distribute it, with pros/cons and math (square root law vs. analytical).
2. Provide suggested safety stock formula outputs for central and regional nodes per SKU (example line for one SKU).
3. Output JSON sample for a small set of SKUs (up to 10): [{"product_sku","central_safety_stock","regional_safety_stock_by_region": {...},"reorder_policy"}]
4. Provide 3 implementation steps and required IT/data capabilities for MEIO.

Return JSON and a short paragraph summarizing tradeoffs.

You are ChatGPT-5.5. Generate an actionable plan to reduce obsolete and slow-moving inventory for a product category. Inputs:
- {{INVENTORY_SNAPSHOT_CSV}} : CSV [product_sku, on_hand_qty, last_sale_date, purchase_cost, location]
- {{SLOW_MOVING_DAYS}} : integer threshold (e.g., 180)
- {{DISPOSITION_OPTIONS}} : list (e.g., ["discount", "bundle", "return_to_supplier", "recycle"])

Task:
1. Identify SKUs meeting slow-moving/obsolescence criteria and prioritize by carrying cost.
2. For top 20 SKUs, recommend disposition option and expected recovery percentage with rationale.
3. Produce a phased 90-day action plan with owners and KPIs (units to recover, expected cash recovered).
4. Output JSON: {"identified_skus":[...],"plan":[{"day","action","owner","expected_outcome"}]}

Include 3 negotiation templates for suppliers (return or buyback) and one email template for internal stakeholders.

Section 3 — Logistics Planning

Seven prompts for routing, carrier selection, warehouse layout, and cost-efficient transportation planning.

You are ChatGPT-5.5. Optimize daily delivery routes for a fleet. Inputs:
- {{DELIVERY_POINTS_CSV}} : CSV [stop_id, address, earliest_delivery_time, latest_delivery_time, demand_units]
- {{VEHICLE_FLEET_JSON}} : JSON [{"vehicle_id","capacity_units","start_location","start_time","end_time"}]
- {{DISTANCE_MATRIX_CSV}} : CSV [from_id,to_id,drive_minutes,drive_miles] (optional: if not provided, say so)
- {{SERVICE_TIME_MIN}} : average service time per stop in minutes

Task:
1. Formulate a feasible route plan minimizing total distance or total drive minutes while respecting time windows and capacities.
2. Provide routes per vehicle with ordered stops, estimated start/end times, total miles, and utilization.
3. Output JSON: {"routes": [{"vehicle_id","stops_ordered":[{"stop_id","eta","etd"}],"total_miles","total_minutes","utilization_percent"}], "summary_metrics": {"total_miles","vehicles_used","on_time_rate_est"}}

If distance matrix is not provided, request geocoding permission or instructions to generate distances.

You are ChatGPT-5.5. Compare carrier options for a set of lanes and recommend a mix for cost, service, and risk. Inputs:
- {{LANES_CSV}} : CSV [lane_id, origin, destination, avg_weekly_volume_units, avg_weight_kg, required_delivery_days]
- {{CARRIER_OFFERS_CSV}} : CSV [carrier_id, lane_id, rate_per_kg, min_fee, lead_time_days, on_time_percent, liability_limit_usd]
- {{RISK_PARAMETERS_JSON}} : {"preferred_on_time_threshold": percent, "max_liability_required": USD}

Task:
1. For each lane, compute total expected transport cost and filter carriers that meet service and liability constraints.
2. Score carriers by cost, service, and risk, and recommend primary and backup carriers per lane.
3. Output JSON: [{"lane_id","recommended_carrier","score_breakdown":{"cost_score","service_score","risk_score"},"annual_savings_vs_baseline"}]

Provide 3 negotiation levers to reduce cost or improve service for high-spend lanes.

You are ChatGPT-5.5. Propose a slotting optimization plan to reduce travel time and improve pick efficiency. Inputs:
- {{SKU_MASTER_CSV}} : CSV [product_sku, dimensions_cm, weight_kg, weekly_units_picked, cube_m3]
- {{CURRENT_SLOT_ASSIGNMENTS_CSV}} : CSV [product_sku, aisle, bay, level, slot_id]
- {{PICK_PROFILE_JSON}} : {"pick_type": "single_line"/"multi_line", "avg_lines_per_order": integer}

Task:
1. Analyze pick frequency and product characteristics to propose new slot assignments that minimize travel distance for top picks.
2. Suggest slotting zones (fast movers, medium, slow) and put-away priorities.
3. Output JSON: {"recommended_slots":[{"product_sku","new_slot_id","zone","expected_minutes_saved_per_week"}], "implementation_steps":["physical moves per day", "relabeling plan", "training notes"], "estimated_roi_weeks"}

Include 3 considerations when integrating slotting changes with WMS wave/pick strategies.

You are ChatGPT-5.5. Identify consolidation opportunities to shift shipments from TL to LTL or optimize LTL consolidation. Inputs:
- {{SHIPMENTS_CSV}} : CSV [shipment_id, origin, destination, weight_kg, cube_m3, ship_date, carrier]
- {{CURRENT_ROUTING_RULES_JSON}} : (optional)
- {{CONSOLIDATION_CENTER_LOCATIONS}} : list of DC addresses or IDs (optional)

Task:
1. Identify shipments that could be consolidated within 24-72 hour windows based on origin/destination proximity and timing.
2. Estimate cost savings vs current routing assuming consolidation center(s) available.
3. Output JSON: {"opportunities":[{"group_shipment_ids","consolidated_weight","estimated_cost_savings","time_delay_hours"}], "recommended_consolidation_windows","organizational_impacts"}

Provide 3 operational rules to implement consolidation without harming service levels.

You are ChatGPT-5.5. Assess feasibility of a cross-docking operation for an inbound flow. Inputs:
- {{INBOUND_SCHEDULE_CSV}} : CSV [eta_date, vendor_id, inbound_pallets, inbound_sku_counts]
- {{OUTBOUND_DEMAND_CSV}} : CSV [date, destination, sku, needed_pallets]
- {{DC_CAPACITY_JSON}} : {"dock_doors": int, "staging_capacity_pallets": int, "labor_shifts": int}

Task:
1. Map inbound windows to outbound demand within 24 hours.
2. Calculate required dock and staging capacity for peak days and identify gaps.
3. Output JSON: {"crossdock_feasible": true/false, "required_changes":["increase_doors","shift_labor","temporary_staging"], "estimated_weekly_cost_change_usd"}

Include 3 recommended KPIs to monitor if cross-docking is implemented (e.g., dwell time, percent cross-docked). 

You are ChatGPT-5.5. Create a routing plan and risk mitigation checklist for perishable cold-chain shipments. Inputs:
- {{PERISHABLE_SKUS_JSON}} : [{"product_sku","required_temperature_celsius","max_transit_hours"}]
- {{LANES_CSV}} : CSV [origin,destination,avg_transit_hours,typical_temperatures_C]
- {{CARRIER_CAPABILITIES_JSON}} : [{"carrier_id","has_refrigerated_trailers":true,"avg_temperature_stability_score":0-1}]

Task:
1. Identify lanes and carriers meeting temperature and transit time constraints.
2. Propose routing plans and packaging requirements (e.g., gel packs, active refrigeration).
3. Output JSON: {"lane_plans":[{"lane_id","carrier_id","expected_transit_hours","risk_level","contingency_actions"}], "cold_chain_checklist": [...]}

Add recommended monitoring telemetry (temporal frequency) and alert thresholds for temperature excursions.

You are ChatGPT-5.5. Compute cost-to-serve at customer or SKU-level to inform pricing and account profitability decisions. Inputs:
- {{FULFILLMENT_COSTS_CSV}} : CSV [order_id, customer_id, sku, pick_cost_usd, pack_cost_usd, transport_cost_usd, returns_cost_usd]
- {{CUSTOMER_SEGMENT_JSON}} : {"customer_id":"segment_name"} optional

Task:
1. Aggregate cost-to-serve per customer and per SKU, and compute profitability vs average revenue (if revenue provided).
2. Identify the bottom 10% profitability accounts and top drivers (e.g., high returns, low order size).
3. Output JSON: {"by_customer":[{"customer_id","segment","avg_cost_to_serve","orders_per_year","profitability_rank"}], "recommendations":["price tiers","minimum order thresholds","fulfillment model changes"]}

Provide 3 suggested pricing or service adjustments for low-profit customers.

Section 4 — Vendor Risk Assessment

Seven prompts to assess supplier scoring, create risk matrices, and design contingency plans.

You are ChatGPT-5.5. Create and apply a supplier scoring model to rank suppliers. Inputs:
- {{SUPPLIER_DATA_CSV}} : CSV [supplier_id, on_time_percent, quality_defects_ppm, lead_time_days, financial_rating_score, capacity_utilization_percent]
- {{WEIGHTS_JSON}} : {"on_time":0.25,"quality":0.30,"lead_time":0.20,"financial":0.15,"capacity":0.10} (optional)

Task:
1. Normalize metrics and compute a composite score between 0-100 using provided or suggested weights.
2. Classify suppliers into tiers (A/B/C) and provide top 10 at-risk suppliers based on score and criticality.
3. Output JSON: [{"supplier_id","score","tier","weaknesses":[...],"recommended_mitigation_actions":[...]}]

Explain how to calibrate weights for strategic vs tactical categories and provide two visualization ideas for sourcing committees.

You are ChatGPT-5.5. Generate a supplier risk matrix and heatmap categorized by likelihood and impact. Inputs:
- {{SUPPLIER_RISK_FACTORS_CSV}} : CSV [supplier_id, disruption_likelihood_score_0to1, impact_score_0to1, dependency_level (high/medium/low)]
- {{CRITICAL_SKUS_JSON}} : {"supplier_id":[sku1,sku2,...]}

Task:
1. Create a 3x3 matrix (Low/Medium/High likelihood × Low/Medium/High impact) and place suppliers accordingly.
2. For each high-high cell supplier, provide a short contingency action (3 steps).
3. Output JSON: {"matrix_cells": [{"cell":"High-High","suppliers":[...],"recommended_contingency":[...]}], "heatmap_summary_metrics":{"percent_suppliers_high_risk","top_impacted_skus"}}

Suggest two governance cadences for reviewing the heatmap (frequency and stakeholders).

You are ChatGPT-5.5. Evaluate supplier financial health and define early warning indicators (EWIs). Inputs:
- {{SUPPLIER_FINANCIALS_CSV}} : CSV [supplier_id, period, revenue_usd, ebitda_usd, current_ratio, debt_to_equity, cash_on_hand_usd]
- {{TRADE_PAYMENTS_CSV}} : CSV [supplier_id, invoice_date, payment_date, payment_amount_usd]

Task:
1. Flag suppliers with declining revenue, compressing margins, deteriorating liquidity, or late payment patterns.
2. Define 5 EWIs with thresholds (e.g., current_ratio < 1.0, revenue decline > 10% q/q).
3. Output JSON: [{"supplier_id","financial_flags":[...],"ewi_scores":0-1,"recommended_actions":[...]}]

Provide two supplier engagement scripts tailored for early-stage financial concern (one conciliatory, one escalatory).

You are ChatGPT-5.5. Assess risk exposure of suppliers to geopolitical events and natural disasters. Inputs:
- {{SUPPLIER_LOCATION_CSV}} : CSV [supplier_id, country, region, city, site_coordinates]
- {{RISK_EVENT_HISTORY_CSV}} : CSV [event_date, location, event_type, severity]
- {{CRITICAL_SKUS_JSON}} : {"supplier_id":[...]} optional

Task:
1. For each supplier, compute exposure score combining event history, country risk index, and criticality of supplied SKUs.
2. Identify suppliers in "high exposure" zones and map top impacted SKUs.
3. Output JSON: [{"supplier_id","exposure_score","events_in_window":[...],"recommended_contingency_locations": [...]}]

Add two strategic actions for mitigating geographical concentration risk (e.g., second sourcing, inventory pre-positioning).

You are ChatGPT-5.5. Produce a supplier-specific contingency and business continuity plan (BCP) template tailored to supplier risk profiles. Inputs:
- {{SUPPLIER_PROFILE_JSON}} : {"supplier_id","criticality","lead_time_days","single_sourcing":true/false,"location"}
- {{RISK_SCENARIOS}} : list (e.g., ["strike","factory_fire","port_closure","raw_material_shortage"])

Task:
1. For each risk scenario, provide 6 operational steps to mitigate disruption and estimated time-to-recovery assumptions.
2. Include contact list template, escalation matrix, interim sourcing options and a checklist for readiness.
3. Output JSON: {"supplier_id","bcp": {"scenarios": [...],"escalation_matrix": [...],"interim_sourcing_options": [...]}, "implementation_timeline_days"}

Also include two sample SLA clauses to include in contracts for continuity obligations.

You are ChatGPT-5.5. Generate a supplier audit checklist and convert audit responses into a risk score. Inputs:
- {{AUDIT_QUESTIONS_TEMPLATE}} : (optional) list of custom questions; if not provided, use best-practice checklist covering quality, governance, environmental, cybersecurity
- {{AUDIT_RESPONSES_CSV}} : CSV [supplier_id, question_id, response, evidence_link]

Task:
1. Map responses to risk weights and compute a normalized audit risk score 0-100.
2. Flag critical non-conformances and recommend corrective action timelines.
3. Output JSON: [{"supplier_id","audit_score","critical_issues":[{"question_id","finding","required_action","due_date"}]}]

Include three guidance notes for remote vs on-site audit tradeoffs and suggested frequency by score tier.

You are ChatGPT-5.5. Prioritize SKUs for dual sourcing based on criticality, current single-sourcing exposure, and cost-to-duplicate. Inputs:
- {{SKU_CRITICALITY_CSV}} : CSV [product_sku, criticality_score_0to1, annual_spend_usd, current_suppliers_count]
- {{SOURCE_MARKET_DATA_CSV}} : CSV [sku, potential_supplier_id, lead_time_days, unit_cost_usd]

Task:
1. Score and rank SKUs by benefit of dual sourcing (risk reduction vs incremental cost).
2. For top 20 candidates, propose sourcing actions (secondary supplier selection, qualification plan, sample/test requirements).
3. Output JSON: [{"product_sku","score","recommended_action","estimated_incremental_cost_percent","time_to_qualify_days"}]

Provide two contract clause suggestions to accelerate secondary supplier onboarding.

Section 5 — Strategic Supply Chain

Seven prompts on network design, nearshoring analysis, sustainability, and longer-term strategic planning.

You are ChatGPT-5.5. Recommend an optimal distribution center (DC) network to minimize combined transportation and facility cost while meeting service constraints. Inputs:
- {{CUSTOMER_DEMAND_CSV}} : CSV [customer_id, latitude, longitude, annual_units]
- {{CANDIDATE_DC_LOCATIONS_JSON}} : [{"dc_id","lat","lon","fixed_annual_cost_usd","capacity_units"}]
- {{TRANSPORT_COST_PER_KM}} : USD per km per unit (or provide matrix)
- {{SERVICE_TIME_THRESHOLD_HOURS}} : maximum allowed transit time from DC to customer

Task:
1. Use a location-allocation heuristic to assign customers to candidate DCs respecting capacity and service time.
2. Compute total annual cost = transport cost + fixed DC costs and present the recommended DC set and assignments.
3. Output JSON: {"selected_dcs":[...],"assignments":[{"customer_id","assigned_dc","annual_transport_cost"}],"total_cost_usd"}

List three sensitivity scenarios to test (e.g., fuel cost +20%).

You are ChatGPT-5.5. Evaluate nearshoring manufacturing or sourcing options including cost, lead-time, and risk tradeoffs. Inputs:
- {{CURRENT_SOURCING_COSTS_CSV}} : CSV [component, current_country, unit_cost_usd, lead_time_days, annual_volume]
- {{NEARSHORE_OPTIONS_CSV}} : CSV [country, unit_cost_usd_estimate, lead_time_days_estimate, tariff_percent, labor_availability_score]
- {{RISK_FACTORS_JSON}} : {currency_volatility, trade_policy_risk_score}

Task:
1. For each nearshore option, compute total landed cost per unit including tariffs and transport and compare lead times and inventory carrying implications.
2. Provide a ranked list by NPV of cost savings over 3-5 years including transition costs.
3. Output JSON: [{"country","unit_landed_cost","lead_time_days","npv_5yr","recommendation","key_risks"}]

Offer three practical steps to pilot nearshoring for one product family.

You are ChatGPT-5.5. Estimate logistics-related CO2 emissions for a set of shipments and identify reduction levers. Inputs:
- {{SHIPMENTS_CSV}} : CSV [shipment_id, mode (truck/air/sea/rail), distance_km, weight_tonnes, load_factor_percent]
- {{EMISSIONS_FACTORS_JSON}} : {"truck_kgCO2_per_tkm", "air_kgCO2_per_tkm", ...} (if omitted, use standard industry values and state them)

Task:
1. Calculate total CO2 emissions per shipment and aggregate by mode and lane.
2. Identify top 10-highest emission lanes and propose 5 levers to reduce emissions (mode shift, consolidation, packaging reduction, routing efficiency, higher load factor).
3. Output JSON: {"total_emissions_tonnes","by_mode":[...],"top_lanes":[...],"recommended_levers":[...]}

Provide one short calculation example showing formula used for a single shipment.

You are ChatGPT-5.5. Create scenario plans and decision trees for a major supply shock (e.g., supplier factory shutdown for 90 days). Inputs:
- {{CRITICAL_SKUS_JSON}} : [{"product_sku","annual_volume","current_lead_time_days","single_sourced":true/false}]
- {{ALTERNATIVE_OPTIONS_CSV}} : CSV [sku, alt_supplier_id, alt_lead_time_days, alt_unit_cost]
- {{INVENTORY_BUFFER_DAYS}} : current buffer days

Task:
1. Define 3 shock scenarios (moderate, severe, catastrophic) and corresponding triggers.
2. For each scenario, provide a decision tree with actions (use buffer, expedite air, alternative supplier, demand rationing) and expected cost/time impact.
3. Output JSON: {"scenarios":[{"name","trigger_conditions","decision_tree":[...]}],"recommended_triggers_for_activation":[...]}

Include two KPIs to monitor for automatic scenario escalation.

You are ChatGPT-5.5. Draft a reverse logistics and circularity strategy for returned products and end-of-life items. Inputs:
- {{RETURN_RATES_CSV}} : CSV [sku, return_rate_percent, reason_codes]
- {{PRODUCT_REPAIRABILITY_JSON}} : {"product_sku":{"repairable_percent","remanufacture_value_percent"}}
- {{REVERSE_LOGISTICS_COSTS_PER_UNIT}} : estimate USD (optional)

Task:
1. Segment returns by disposition pathway (restock, refurbish/repair, recycle, landfill) with estimated volumes and costs.
2. Recommend infrastructure (collection points, inspection hubs), KPIs, and a 12-month pilot plan for circular initiatives.
3. Output JSON: {"disposition_mix":[...],"expected_recovery_value_usd","pilot_plan":[{"month","activity","expected_outcome"}]}

Provide two partnership models (3rd-party reverse logistics, in-house) with pros/cons and cost considerations.

You are ChatGPT-5.5. Create a prioritized digital transformation roadmap for core supply chain capabilities. Inputs:
- {{CURRENT_TECH_STACK_JSON}} : {"erp": "name", "tms": "name", "wms":"name", "analytics":"name"}
- {{KEY_PAINS_LIST}} : list of top pain points (e.g., stockouts, data latency, manual planning)
- {{BUDGET_USD}} : target digital transformation budget for planning period

Task:
1. Propose a 12-24 month roadmap with initiatives prioritized by value and feasibility (e.g., demand forecasting upgrade, real-time visibility, MEIO implementation).
2. For each initiative provide estimated cost range, timeline, KPIs, and required organizational capabilities.
3. Output JSON: {"roadmap":[{"initiative","priority","estimated_cost_usd","timeline_months","expected_benefit_kpis"}], "change_management_steps":[...]} 

Add two quick-win pilots to start within 90 days with minimal investment.

You are ChatGPT-5.5. Help set realistic supply chain sustainability targets (Scope 1-3 focus on logistics and purchased goods) and design a supplier engagement program. Inputs:
- {{CURRENT_EMISSIONS_BASELINE_JSON}} : {"logistics_tonnes_co2","purchased_goods_tonnes_co2","year"}
- {{SUPPLIER_EMISSIONS_COVERAGE_PERCENT}} : percent of spend covered by supplier emission data
- {{TIME_HORIZON_YEARS}} : integer (e.g., 5)

Task:
1. Propose achievable targets (absolute and intensity-based) for the next {{TIME_HORIZON_YEARS}} years with rationale and interim milestones.
2. Design a supplier engagement program including data collection, incentives, capacity building, and procurement levers.
3. Output JSON: {"targets":[{"year","logistics_target_tonnes","purchased_goods_target_tonnes"}],"supplier_program_steps":[...],"metrics_to_track":[...]}

Provide two suggested KPIs for executive reporting and one supplier survey template to collect emissions data.

Conclusion & Next Steps

These 35 prompts are designed to be directly usable with ChatGPT-5.5. For best results:

• Replace each variable (e.g., {{PRODUCT_SKU}}, {{SALES_HISTORY_CSV}}) with the relevant dataset or parameter before submitting.
• Request JSON outputs for easy downstream processing and integrate them with your analytics or ERP/TMS via automation.
• Chain prompts: use outputs from forecasting prompts as inputs for inventory optimization or logistics planning prompts to create end-to-end workflows.

If you’d like, I can:

• Customize any prompt to match your internal naming conventions or ERP fields.
• Create example CSV/JSON payloads for testing the prompts.
• Build a short “playbook” describing how to operationalize these prompts in an automation pipeline.

Ready to get started? Tell me which area you want to prioritize (Demand Forecasting, Inventory Optimization, Logistics Planning, Vendor Risk Assessment, or Strategic Supply Chain) and provide one sample dataset or a small example table, and I will adapt a prompt for your specific environment.