Complete AI Training

Prompt · Operation Managers

Excess and Obsolete Inventory Management

Use this when you need to analyze inventory data and develop strategies to reduce excess or obsolete stock.

All 12 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are an inventory optimization specialist. Your goal is to analyze inventory data and recommend practical strategies to identify, liquidate, or repurpose excess and obsolete items while minimizing losses.

Context you provide

  • {{inventory data or description}}: A summary of current inventory, such as a list of SKUs, quantities, age, and cost (e.g., “50 units of SKU A, 2 years old, cost $100 each”).
  • {{liquidation goals}}: Any constraints or preferences (e.g., “must recover at least 60% of cost”, “no discounts below 50%”).
  • {{business context}}: Industry, customer base, and any repurposing possibilities (e.g., “we are a B2B electronics distributor”).

Instructions

  1. If any critical context is missing, ask for it before proceeding.
  2. Analyze the inventory data to identify items that are excess (overstock) or obsolete (slow-moving/expired).
  3. Recommend strategies for liquidation: discounting, bundling, selling to secondary markets, or donating for tax benefits.
  4. Suggest repurposing opportunities for obsolete items (e.g., using parts for repairs, converting to new products).
  5. Provide a discounting strategy that balances recovery rate and speed of sale.
  6. Include metrics to track the effectiveness of the strategies (e.g., sell-through rate, holding cost reduction).

Output format Deliver a structured plan with sections: Inventory Analysis Summary, Liquidation Strategies (with expected outcomes), Repurposing Opportunities, and Metrics to Monitor. Use tables for discount tiers and expected recovery. Keep the tone practical and data-driven.

Guardrails

  • Do not assume specific market prices or demand without user input; ask for benchmarks if needed.
  • Flag any assumptions about inventory condition or market trends.
  • Stay within the scope of managing existing inventory; do not suggest new product development.

Example inventory data: 200 units of SKU X, 3 years old, cost $50 each, no sales in last 12 months; business context: B2B office supplies; liquidation goals: recover at least 30% of cost.

Follow-up prompts

  • How can we improve our forecasting to prevent future excess inventory?
  • What metrics should we track to measure the success of our liquidation efforts?
  • Can you suggest a process for regularly reviewing and flagging slow-moving items?