Merchandising & Buying
Product description writing
Generate first-draft product descriptions from attributes, imagery, and brand guidelines. Buying team reviews, edits, and approves before publish.
60–80%
reduction in description drafting time
Opportunity assessment
Minor improvement. Small efficiency gain with limited effect on overall turnover or bottom line.
Very easy to implement. Ready-to-use tools exist. Can be up and running in days or weeks with minimal technical resource.
Light data requirements. Uses straightforward inputs — documents, product descriptions, customer records — that are usually accessible with minimal prep.
Very low risk. Fully internal use. A person checks everything before it goes further. Worst case is a minor internal inconvenience.
Light people impact. A new tool slots into an existing workflow. Minimal training needed. Most people will adapt quickly.
Tooling required
Things to consider
Walmart used LLMs to create or improve 850M+ data points in its product catalogue, achieving 100x productivity versus manual effort. E-commerce grew 22% globally (Retail Dive).
Brand guidelines must be clearly documented and embedded in the system prompt — inconsistent guidelines produce inconsistent outputs.
Define a review workflow before launch: who reviews, what they check for, and what the approval step looks like.
Start with a single product category to calibrate tone and quality before scaling across the full range.
Measure quality by tracking the edit rate — if reviewers are rewriting more than 30% of the content, the prompt needs refinement before scaling to the full range.
Experiment starter: Pick 20 products from one category. Run them through a well-prompted LLM using your brand guidelines and have the content team rate outputs blind against their own drafts. If 70%+ are rated usable with light editing, the case is made.
Go deeper in the playbook
Section — Opportunity Identification, including the AI Opportunity Assessment ScorecardSection — The Experimentation FrameworkThis is an augmentation opportunity — see the relevant playbook section for how to approach it.More in Merchandising & Buying
Supplier spec sheet extraction
Extract structured product data from unstructured supplier spec sheets, PDFs, and email attachments. Outputs clean records ready for system upload.
Range review analysis
Summarise sales performance, markdown rates, and return data by category to surface underperformers and inform ranging decisions.
Buyer brief generation
Draft structured buying briefs from season parameters, trend references, and last-year performance data. Reduces prep time before supplier meetings.
AI Transformation Playbook
Ready to assess your own opportunities?
The playbook gives you the full 150-opportunity directory, scoring tools, and 100+ templates for every stage of an AI transformation programme.