Deflection rate
Deflection rate is the share of support contacts resolved without a human agent. It is a common target and a misleading one: a deflected ticket and a resolved question are not the same event. A user who gives up counts as deflected. The better metric is resolution: whether the person actually got what they came for.
New to the category? Read what AI customer support is and how it works.
Why is deflection a flawed metric?
Because it measures the absence of a ticket, not the presence of a solution. A confusing bot that makes users abandon their question deflects beautifully and helps no one. Optimising for deflection can make a support experience worse while the dashboard turns green, which is why resolution and repeat-question rate matter more.
What should you measure instead?
Resolution rate (did the user complete the task) and repeat-question rate, which catches the deflections that didn't actually work. An honest system also reports sessions where it found nothing and said so, because a clean hand-off is a better outcome than a false resolution that sends someone in a circle.
What does deflection look like in practice?
A user asks a bot how to export invoices, gets a link to a help article, and closes the chat without finding the button. The dashboard counts the conversation as deflected because no ticket was opened, yet the user still cannot export the invoice and is likely to ask the same question again.
How does Peeve handle deflection?
Peeve is built around resolution rather than deflection. It shows the user the step on the live screen, reports the routes where users stall in their own words, and does not bill conversations where it found nothing and said so, so an honest hand-off is never counted against you as a failure.