Anna, who works in customer success at Tars, tells this one on herself. She ordered gym gloves, and on delivery day realized the shipping address was an old hostel where packages get left in a box outside with no call and no verification. The item was non-refundable and the parcel was already out for delivery. She went to the support chat to stop it. The bot told her not to worry, her package was out for delivery, which was precisely the problem, and then offered only template options. No free text, no way to explain the situation, no route to a person.

By the system's own metrics that was a successful conversation. She asked for delivery details and got the courier's number, the status, and the tracking number. The question was answered. The situation was not. Watch this if your support reporting looks healthy and your customers do not sound it.

What this video covers

• What most companies count as a successful AI conversation, and why the customer often disagrees
• A support chat that answered the question correctly, offered only template replies, and left no route to a human
• The opposite case, a repeat customer refunded immediately because the system had enough context to know the complaint was genuine
• Why agents optimized to answer questions struggle with customers who arrive with situations
• The three things she argues a system has to understand, context, intent, and when to stop trying and bring in a person

Chapters

• 0:00 How customer support has changed
• 0:43 The out for delivery notification
• 1:22 The support chat that counted as a success
• 2:34 The opposite experience
• 3:18 Accuracy is not experience