Customer Service
Return reason categorisation
Automatically classify free-text return reasons into structured categories. Feeds merchandising and quality teams with actionable data.
80–90%
reduction in manual classification effort
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.
Minimal data complexity. Works with whatever is readily to hand. No special data infrastructure needed. Most businesses can start immediately.
Very low risk. Fully internal use. A person checks everything before it goes further. Worst case is a minor internal inconvenience.
Very easy to absorb. Runs quietly in the background or gives people a helpful new input. Makes everyday work easier with almost no friction.
Tooling required
Things to consider
Define your return reason taxonomy before building — 8-12 clear categories with examples are easier to classify into than vague or overlapping ones.
Spot-check accuracy monthly: categories drift as language patterns change, and the model may need prompt updates to stay accurate.
The value is in what you do with the data — ensure the categorised output actually reaches the merchandising and QC teams in a usable format.
The most actionable insight comes from cross-referencing return reasons with specific products, suppliers, or seasons. Ensure the categorised output includes those dimensions, not just the reason alone.
Experiment starter: Export three months of free-text return reasons. Prompt an LLM to classify them against a pre-agreed taxonomy and manually validate a sample of 100. If classification accuracy exceeds 85%, you have a working system — automate from there.
Go deeper in the playbook
Section — Opportunity Identification, including the AI Opportunity Assessment ScorecardSection — The Tooling LandscapeThis is an automation opportunity — see the relevant playbook section for how to approach it.More in Customer Service
Complaint triage and first-draft response
Classify incoming complaints by type and urgency, then generate a first-draft response. Agent reviews, personalises, and sends. Faster turnaround, consistent tone.
Knowledge base chatbot (FAQ deflection)
Answer common customer questions using a RAG system over the knowledge base. Deflects repeat queries from contact centre. Escalates complex issues to humans.
Customer feedback synthesis
Aggregate and summarise customer reviews, survey responses, and support tickets into themes. Weekly digest for product and commercial teams.
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.