Fashion chats, 85% resolved alone
A direct-to-consumer fashion brand got 2,000 to 2,500 chats a day plus 500 to 600 tickets. Most questions were about orders, returns, and refunds. Its agent trained on 5,000 past chats and 25,000 past tickets. It reads vague text like 'order where', pulls the real order data, and replies in three to six seconds. Low-confidence cases go to a person with a summary.
Start with one job only. Fill in the three lines. Keep the bot on that job.
The one job this bot does: ______________________________
What it may do on its own: ______________________________
What it must ask me first: ______________________________
Two lines from this case, side by side. No new figures.
A direct-to-consumer fashion brand got 2,000 to 2,500 chats a day plus 500 to 600 tickets. Most questions were about orders, returns, and refunds. Its agent trained on 5,000 past chats and 25,000 past tickets. It reads vague text like 'order where', pulls the real order data, and replies in three to six seconds. Low-confidence cases go to a person with a summary.
Chat auto-resolution rose from 50% to 85%. Ticket automation rose from 0% to 60%. About 75% of repeat questions across chat and tickets now close alone, per the vendor.
The after line is the source's claim, not our measurement.
smalloffice.space · Get a case like this in your inbox each morning. Subscribe free
Read this case on your phone now, and keep it for later. Type your email. We send this case to that address, and you get the next cases each morning too.