AI Playbook
for Retail & E-Commerce

You are a merchandise planner calculating open-to-buy for the upcoming buying period.

Planning data:
[PASTE: Department/category | Planned sales | Planned beginning of month inventory | Planned end of month inventory | Planned markdowns | Planned shrinkage | Receipts already on order]

Calculate open-to-buy (OTB):
1) Planned inventory needed = Planned EOM inventory + Planned sales + Planned markdowns + Planned shrinkage
2) Available inventory = Planned BOM inventory + Receipts already on order
3) OTB = Planned inventory needed − Available inventory
4) OTB by month — break the total OTB into a monthly receipt flow; front-load or back-load based on selling curve
5) Flag any department with negative OTB (over-bought) — receipts already exceed planned inventory need

Output: OTB calculation by department and month. Over-bought departments requiring PO cancellation or deferral. Available OTB to commit to new buys.

You are a merchandise manager analyzing Gross Margin Return on Inventory Investment (GMROI).

Category data:
[PASTE: Category | Annual sales | Cost of goods sold | Gross margin $ | Gross margin % | Average inventory at cost | Inventory turns]

Calculate:
1) GMROI = Gross margin $ ÷ Average inventory at cost
2) Alternatively: GMROI = Gross margin % × Inventory turns
3) Rank categories by GMROI — highest return on inventory investment first
4) Benchmark comparison — GMROI below 1.0 means the category is not earning back its inventory investment; target varies by category type (hardlines typically >2.0, softlines >1.5)
5) Action recommendations — low GMROI categories: improve turns / improve margin / reduce inventory / exit

Output: GMROI analysis table. Category ranking. Below-benchmark categories with specific action recommendation.

You are a buyer reviewing the assortment plan for a product category.

Assortment data:
[PASTE: SKU | Description | Category | Price point | Last season units sold | This season planned units | Margin % | New or carryover | Any performance flags]

Review:
1) Assortment width vs. depth — are you offering too many choices (wide and shallow) or too few options but well-stocked (narrow and deep)? What does your customer need?
2) Price ladder — is there a logical progression from entry-level to premium? Any gaps or overlaps?
3) 80/20 analysis — what % of SKUs generate 80% of category revenue? Are low-contribution SKUs worth the space and inventory investment?
4) New vs. carryover balance — new items drive excitement; carryover items provide revenue stability; what's the right ratio for this category?
5) Exit recommendations — SKUs with poor prior-season sell-through that should not be reordered

Output: Assortment review. Exit SKU list. Price ladder assessment. New vs. carryover balance recommendation.

You are a buyer preparing for a vendor line review and negotiation.

Vendor data:
[PASTE: Vendor | Category | Annual sales | Gross margin % | Sell-through % | Returns rate | Markdown support received | On-time delivery % | Any quality or compliance issues | Market alternatives available]

Build the negotiation brief:
1) Our leverage — sales volume, growth trend, share of their business, ability to reduce orders or switch vendors
2) Their leverage — unique product, no viable alternatives, strong consumer demand
3) Target outcomes — priority 1: cost improvement / priority 2: markdown support / priority 3: dating and payment terms
4) Opening position vs. target vs. walk-away for each negotiation point
5) Concessions to offer — volume commitment / faster payment / fewer returns / exclusive styles

Output: Vendor negotiation brief. Leverage assessment. Target outcomes. Opening and target positions. Concessions available.

You are a merchandise manager analyzing sell-through rates to make reorder and markdown decisions.

Sell-through data:
[PASTE: SKU | Description | Season | Units received | Units sold | Units on hand | Sell-through % | Weeks on floor | Target sell-through % | Selling season remaining (weeks)]

For each SKU:
1) Sell-through % = Units sold ÷ Units received × 100
2) Current sell-through vs. target — ahead, on track, or behind?
3) Projected final sell-through at current rate = (Units sold ÷ Weeks on floor) × Total selling season weeks
4) At-risk SKUs — items tracking to end the season with excess inventory at current sell rate
5) Action recommendation:
   - Ahead of plan: consider reorder if vendor available
   - On track: no action
   - Behind plan: markdown, move, or promotional push

Output: Sell-through analysis. Projected final sell-through by SKU. Reorder candidates. Markdown or action list for at-risk SKUs.

You are a merchandise planner developing a markdown strategy for end-of-season clearance.

Inventory data:
[PASTE: SKU | Retail price | Cost | Units on hand | Sell-through % to date | Weeks of selling season remaining | Target sell-through to clear | Current margin %]

Build the markdown strategy:
1) Markdown depth required — to sell through remaining units in the remaining weeks, what discount % is needed?
2) Break-even markdown — at what price does the item cover its cost? (cost ÷ (1 − target margin) = minimum price)
3) Margin at markdown — gross margin $ per unit at proposed markdown; total margin impact
4) Markdown sequence — start with a modest markdown, then deepen; show the sequence and trigger points
5) Last resort — items that won't clear even with deep markdown; liquidation, donation, or vendor return options

Output: Markdown strategy by SKU. Margin impact analysis. Markdown sequence with trigger points. Liquidation plan for uncleared items.

You are a merchandise director evaluating a private label development opportunity.

Analysis data:
[PASTE: Category | Current national brand pricing | Current national brand margin % | Proposed private label retail price | Estimated private label cost | Projected margin % | Volume required to justify development | Customer price sensitivity in this category]

Analyze:
1) Margin improvement — private label margin % vs. national brand margin %
2) Price-value positioning — private label typically priced 15–25% below national brand while maintaining higher margins
3) Volume requirement — at proposed margin improvement, what volume is needed to recover development investment?
4) Brand risk — are customers loyal to national brands in this category, or is it a commodity purchase?
5) Supplier landscape — are there capable manufacturers who can produce to your specifications?

Output: Private label opportunity analysis. Margin improvement potential. Volume break-even. Risk assessment. Go/no-go recommendation.

You are a visual merchandising manager reviewing planogram performance.

Planogram data:
[PASTE: Category/fixture | Total facings | Sales per facing | Average inventory per facing | Turn rate | Out-of-stock frequency | Customer conversion rate (if available) | Any shopper feedback]

Review:
1) Sales per facing — which products deserve more facings based on sales velocity?
2) Facings vs. velocity mismatch — high-velocity items with too few facings cause stockouts; low-velocity items with too many facings waste space
3) Category adjacency — are complementary products placed together to drive basket size?
4) Eye-level vs. floor placement — are the highest-margin or highest-velocity items at eye level?
5) Space productivity — sales per linear foot by section; underperforming sections vs. benchmark

Output: Planogram review. Facing reallocation recommendations. High-priority restocking locations. Space productivity analysis.

You are a buyer planning the seasonal buy.

Planning data:
[PASTE: Category | Last season sales | Last season units | Last season sell-through % | This season sales plan | Average retail price | Average cost | Key delivery windows | Lead times by vendor | Open-to-buy budget]

Build the seasonal plan:
1) Units to buy = This season sales plan ÷ Average retail price
2) Cost dollars to commit = Units × Average cost
3) Delivery timing — distribute receipts across the season to match the selling curve; don't front-load all receipts
4) Vendor allocation — how to distribute the buy across your vendor base; concentration risk
5) Chase/hold-back strategy — buy 70–80% upfront; hold 20–30% OTB to chase bestsellers

Output: Seasonal buy plan by category and delivery window. Cost commitment schedule. Chase budget available. Vendor allocation.

You are a merchandise manager preparing quarterly vendor scorecards.

Vendor data:
[PASTE: Vendor | Category | Sell-through % | Gross margin % | On-time delivery % | Fill rate % | Return rate % | Quality claims | Markdown support provided | Compliance issues]

Score each vendor across:
1) Product performance — sell-through and margin vs. category average
2) Operational reliability — on-time delivery and fill rate
3) Partnership quality — markdown support, responsiveness, compliance
4) Risk assessment — any quality, compliance, or financial stability concerns

Classify: Preferred / Core / Developing / Exit.
For Exit vendors: exit timeline and replacement strategy.

Output: Vendor scorecard. Tier classification. Exit vendor list with replacement plan. Partnership improvement requests for developing vendors.

You are a category manager preparing the quarterly category review.

Category data:
[PASTE: Category | Revenue | Revenue vs. plan | Revenue vs. prior year | Gross margin % | Margin vs. plan | Inventory turns | GMROI | Market share (if known) | Customer satisfaction indicators]

Review:
1) Financial performance — revenue and margin vs. plan and prior year; growing or declining?
2) Inventory productivity — turns and GMROI vs. target; is inventory working hard enough?
3) Assortment health — sell-through rates, SKU productivity, any excess inventory building
4) Customer signals — any data on customer satisfaction, return rates, or reviews by category
5) Strategic recommendation — invest / maintain / rationalize / exit for each category based on data

Output: Category review report. Financial and inventory performance summary. Assortment health. Strategic recommendation by category.

You are a merchandise manager analyzing lost sales from stockouts.

Stockout data:
[PASTE: SKU | Category | Days out of stock | Average daily units sold (before stockout) | Estimated lost units | Average retail price | Estimated lost revenue | Root cause (forecast miss/PO delay/vendor shortage/DC error)]

Analyze:
1) Total lost revenue — sum of estimated lost revenue across all stockout events
2) Highest-impact stockouts — items where lost revenue was greatest; these are the priority to prevent
3) Root cause distribution — what % of stockouts were forecast-driven vs. supply-driven vs. operational?
4) Repeat stockouts — same SKU stocking out multiple times in the same season; systemic issue
5) Corrective actions — for each root cause, specific process or parameter change to prevent recurrence

Output: Lost sales analysis. Total revenue impact. Root cause breakdown. Corrective actions. Safety stock or reorder parameter updates needed.