Ecommerce Merchandising Audit for an Underperforming Category
Diagnose why a product category underperforms across assortment, navigation, availability, presentation, pricing, and customer intent.
PROMPT GUIDE / ECOMMERCE & RETAIL
Diagnose why a product category underperforms across assortment, navigation, availability, presentation, pricing, and customer intent.
READY-TO-USE PROMPT
Ecommerce Merchandising Audit for an Underperforming Category
COPY THIS PROMPT
Act as a digital merchandiser and retail analytics specialist. GOAL Audit [CATEGORY] for [STORE] and prioritize improvements by evidence and commercial impact. INPUTS - Category page, product feed, taxonomy, filters, search terms, and content - Traffic, click, conversion, revenue, margin, stock, returns, and seasonality - Customer research, competitor observations, and merchandising constraints - Promotion calendar, supplier limits, brand rules, and implementation capacity WORKFLOW 1. Separate demand, discovery, consideration, availability, trust, and price problems 2. Audit assortment gaps, duplication, dead ends, sorting, filters, and product information 3. Map evidence to specific customer intents and funnel stages 4. Estimate impact, confidence, effort, dependencies, and risk for each change 5. Build a measured 30-day improvement sequence REQUIREMENTS - Separate confirmed facts, assumptions, and missing information. - Do not invent measurements, specifications, prices, policies, or results. - Make every recommendation specific, testable, and prioritized. - Identify risks, dependencies, edge cases, and a practical fallback. - Ask focused questions when a missing input would materially change the answer. DELIVERABLE Return a diagnostic scorecard, evidence table, prioritized backlog, quick wins, experiments, ownership plan, and success dashboard.
What this prompt helps you produce
- Root causes separated from symptoms
- Actions tied to customer intent and commercial metrics
- A practical sequence that accounts for inventory and implementation
How to use it
- Replace every bracketed input with real project information.
- Attach representative examples and constraints when available.
- Review assumptions before acting on recommendations.
- Run the proposed checks on a small sample, record results, then revise.
Frequently Asked Questions
Can I use this with incomplete information?
Yes. Leave unknown fields clearly marked. The response should turn them into targeted questions instead of silently filling gaps.
Should I accept the first result?
No. Verify it against real examples, measurements, source material, or stakeholder requirements, then rerun the prompt with corrections.
Which AI model should I use?
Use a model that can follow long structured instructions and provide the context it needs. The quality of the inputs and verification process matters more than a model label.