Glossary/Support Metrics

What is Deflection Rate?

The percentage of support questions resolved by self-service — typically an AI assistant — without creating a ticket or reaching a human agent.

If 1,000 customers ask questions in a month and 620 get their issue resolved by the assistant without filing a ticket, the deflection rate is 62%. Multiplied by cost per ticket, deflection is the most direct way to express a support AI's financial impact.

The honest version of the metric matters. Counting every AI interaction as a deflection inflates the number; counting only confidently-answered questions that did not subsequently become tickets reflects reality. Deflection should also never come at the cost of trapping users who need a human — a low-confidence question that escalates quickly is a success, not a failure.

Deflection rate pairs naturally with gap analysis: the questions that fail to deflect are exactly the list of content to write next.

In BeforeQuery

How BeforeQuery uses this

BeforeQuery meters resolved-versus-escalated outcomes per workspace, applies confidence scoring so only well-grounded answers deflect (in chat and the Support Form Agent), and lets you replay historical tickets through simulations to estimate deflection before going live.

From definition to deployment

Connect a knowledge source and see cited AI answers on your own content in minutes — free, no credit card required.

Get Started Free