Ticket deflection you can actually verify
Deflection is usually counted as tickets that did not get filed. That number cannot tell a customer who found their answer from one who gave up. What separates them is whether the question was answered and whether the visitor could check the source.
The problem
A drop in ticket volume gets read as a win without anyone checking whether the question was answered or the person simply left.
How it works
- 1
Questions are answered at the moment they are asked, on the page where the visitor is already standing — before a contact form is involved.
- 2
Every answer cites the page it came from, so the visitor can confirm it rather than take it on trust.
- 3
A question the site cannot answer is recorded as a knowledge gap instead of being quietly dropped, so the shortfall is visible rather than inferred.
What changes
Fewer repeat tickets on questions your published pages already answer.
A named list of the questions your content does not cover yet.
Deflection you can distinguish from abandonment, because answered and unanswered are recorded separately.
Questions
- How is this different from counting fewer tickets?
- Ticket count alone cannot separate a resolved question from an abandoned one. Recording which questions were answered, and which were not, is what makes the difference legible.
- What happens to questions it cannot answer?
- They go to the knowledge-gaps queue in your dashboard, grouped by how often they came up. That is a list of what to write next, in priority order.
Related
tool
Deflection rate calculator
Most deflection numbers are inflated by counting abandoned conversations as successes. This one keeps them separate, so you see both the honest rate and what a looser count would have claimed.
tool
Customer support cost calculator
Calculates the real cost of your support operation — per conversation, per month and per year — from volume, handling time and loaded hourly cost.
tool
Website support score
Scores a website on how well it could support customers — and how well an AI representative trained on it would perform. Five dimensions, a total out of 100, and the specific gaps behind the score.
industry
AI customer support for SaaS companies
SaaS support is dominated by questions your documentation already answers: what a plan includes, whether a feature exists, how an integration works. RubyRep reads your docs, pricing and changelog and answers those on the site, so trial users get unblocked in seconds instead of waiting on a ticket.
industry
AI customer support for ecommerce stores
Most ecommerce support is four questions wearing different hats: where is it, when will it arrive, can I return it, and will it fit. RubyRep reads your product pages and policies and answers them at the moment of hesitation, which is the moment the sale is won or lost.
industry
AI customer support for healthcare practices
Most calls to a practice are logistics, not medicine: opening hours, what a visit costs, which insurance is accepted, what to bring. RubyRep answers those from your website so reception can focus on patients in front of them — and it stays firmly out of clinical advice.