About this case study: it is based on a business typical of the ones we work with, not a named client, and every number comes from the assumptions at the end of the page. Swap in your own and the sums still work.
The problem
About 900 tickets arrive each month. Six in ten are order status, returns or sizing, all answerable from data the brand already has.
Replies slow down after launches and sales, exactly when customers are most likely to ask.
What we build
- 1
Answers from real data
The assistant reads the Shopify order, tracking, return policy and size guide, and replies in the brand's voice.
- 2
Returns started for the customer
Eligible returns get a link to the returns portal with the order already filled in.
- 3
Clean handover
Anything else, or any upset customer, goes to the team with a short summary of the conversation.
- 4
What people ask
A weekly report lists the top questions, so product pages and the FAQ can answer them first.
Before and after
| Step | Before | After |
|---|---|---|
| Order status ticket | About 5 minutes | Answered automatically |
| Other tickets | Read from the start | Summary ready, about 2 minutes saved |
| Top questions | Guesswork | Weekly report |
Where a person stays in control
Refunds, exchanges outside policy and complaints always go to a person. The assistant cannot change orders.
Running cost
Roughly $150–400 a month for AI usage and the helpdesk integration, depending on ticket volume.
Tools
- Shopify
- Gorgias or the existing helpdesk
- Returns portal
- AI assistant
How the numbers work
- 900 tickets a month at 5 minutes = 75 hours.
- We assume half are fully answered by the assistant (37.5 hours) and the rest save 2 minutes each (15 hours). Check the real share after a month.
- Support time costed at $25 an hour: 52 × $25 = $1,300.
Estimates, not promises. Use the savings calculator with your own hours and costs.
Want this for your business?
A free 30-minute call is enough to tell whether it fits, what it would take and what it would cost.