Deflection and escalation

Two rates sit at the top of Insights, in the strip of figures above the activity chart. They are the numbers a support agent is usually judged on, and they are counted over the same conversations, from what the server itself recorded — never from anything a visitor's browser said happened.

What each one counts#

They are complements over the same set of conversations: the last 30 days of conversations in which somebody asked your twin something. The window is printed beside each rate, so the number and the period it covers can never come apart.

The sentence under each rate on screen is the same one this page is written from. If a caption here and a caption there ever disagreed, one of them would be claiming something hiy doesn't measure — so there is one wording, kept in one place.

Every percentage carries the two numbers it's made of#

A rate is never shown on its own. Inside the same tile sits the count it came from and the window it was counted over — 20 of 25 conversations · Last 30 days — so you can check the arithmetic and see how big the sample was. A percentage whose numerator and denominator are hidden is something you have to take on trust, and these are meant to be numbers you can quote to somebody else.

Under the strip, each rate keeps a block of its own naming what it counts and what it does not. The tile is the number; the block below it is the sentence that number is allowed to be read as.

Below twenty conversations, no percentage at all#

Until twenty conversations have happened in the window, neither rate is stated. The tile shows a dash rather than a number, with how far along you are beside it — 7 of 20 conversations so far — and the block under the strip says Not enough conversations yet in words.

That is the state most twins are in, and it isn't an error. A rate off a handful of people is a story wearing the costume of a measurement. Twenty is where one conversation stops being able to move the headline by more than five points; below it, a single person swings the number. Rather than print something that will swing and then settle, hiy says what it has so far and waits — the count is real, and it is going up.

A busy window says so, rather than guessing#

At the other end, a window can hold more conversations than one read can total exactly. When that happens the tile shows a dash and the block under the strip says so — too many conversations in this window to count exactly — and no rate is stated.

It is deliberately not an approximation. A rate counted from part of a window isn't a slightly-off rate, it's an unknown one, and there would be nothing on the screen to tell it apart from the truth. So the honest answers are a percentage or a reason there isn't one, and never a number with a caveat.

Which agent they are about, and how to change it#

These two rates are one agent's, on a page whose chart above them adds up every agent you own. That is why the line beside them reads These rates cover Ada only — not your other agents.

Next to that line is the agent's name with a chevron. Open it and pick another agent, and Insights reloads showing that agent's rates, teach queue and outcomes — the combined chart and Top questions are unchanged, because they always covered everything. It is the same move as picking an agent in the switcher, without leaving the page you are reading.

It only appears once you have more than one agent: with a single agent there is nothing to change it to, and the scope line isn't printed either.

What these rates do not tell you#

They do not say whether anyone's problem was solved. hiy has no way of observing that and will not invent one. Deflection counts conversations where the agent never said it couldn't answer — that is the absence of an admission, not the presence of a solution. Nothing here is a resolution rate, and it is never described as one.

Deflection is not a claim that nobody was handed off. A handoff is something the visitor's browser reports, and these counts never read it. A conversation where somebody asked for a person, but where the agent never admitted it couldn't answer, is counted as deflected. Your People list and your Inbox are where handoffs are recorded — see Where a lead came from. When your agent hands over, who that reaches and what the visitor reads are yours to set: Handing over to a person. Changing those settings never moves these rates.

They aren't a score you can improve by tidying up. The escalation count includes the questions your teach queue recorded, counted at the moment they were raised. Clearing your queue doesn't move a past rate, because a number the person being measured can change by pressing dismiss isn't a number worth printing.

The questions behind them#

Under the two rates, the paid Founding plan adds the questions your agent recorded a gap for, grouped the same way your teach queue groups them — so you can see what your twin keeps getting asked and can't answer yet, and go teach it.

That list is part of what drove the rates, not all of it. When your agent says it can't answer, hiy records that it happened; it does not store the wording of every question that led to it. So a conversation can count toward the rates above without appearing in the list below them, and the list never claims to be the whole story.

Where the counting happens#

Everything in this strip is counted server-side from your own twin's records: the questions people asked it, the times it said it couldn't answer, the gaps it raised for you, and handoffs recorded against an answer it had already admitted it couldn't give. Nothing is modelled, nothing is estimated, and no number here comes from a visitor's browser asserting something happened.