For the complete documentation index, see llms.txt. Every page on this site is also served as Markdown: append `.md` to any URL, or send `Accept: text/markdown`.
Attensira Logo
Attensira
GEO Glossary

Reference rate

The share of completed AI answer runs, over a defined prompt set, in which a brand or its domain appeared — an observed frequency with a denominator, not a score and not a prediction.

Karl-Gustav KallasmaaKarl-Gustav Kallasmaa, Founder & CEOLast updated

A reference rate is the share of completed AI answer runs, over a prompt set someone defined, in which a brand or its domain appeared in the answer. It is an observed frequency with a stated denominator. It is not a score, not a rank, and not a prediction of future mentions.

The definition is only useful if the denominator travels with it. A bare percentage is not a claim anyone can check; "named in twelve of fifty successful runs across two models over the last seven days" is. Everything else on this page follows from insisting on that second form.

The denominator, precisely

In Attensira the denominator is successful runs in the window: the rate is the number of those runs whose stored answer text named the brand or its domain, divided by all of them, reported as {value, n}. Failed runs are stored but excluded from n, so a day with collection problems yields a smaller sample rather than a distorted rate.

Two values that look adjacent are different facts, and a chart that draws them the same way is lying:

  • value: nullnot measured. Nothing was observed, so nothing can be reported. A model marked tracked: false was never queried; rendering that as a measured zero invents a rejection that never happened.
  • value: 0 with n > 0measured zero. Runs completed and none of them named the brand.

Why rates do not sum, and are not a share

Competitor reference rates use the same denominator as yours. They are independent rates, not slices of a fixed total. A single answer that names you and three competitors raises four rates from one run, which is why adding them can exceed the whole and tells you nothing.

This matters for a field name people misread. Attensira's ShareOfVoice is the brand's own mention rate under an older name — the same number, not a share of anything. Nor is AvgPosition a rank of your brand: it is the mean index of a URL within a model's own citation list, computed per source domain, answering "when this domain is cited, how far down the list does it sit". Attensira computes no visibility score and no sentiment metric, and no predicted probability of being referenced.

How the underlying detection actually works

A mention is a case-insensitive substring match of the brand name or domain against the answer text. There is no entity resolution and no word-boundary check. A brand called Arc matches "march" and "search"; a brand called Notion matches "notional". That error is systematic rather than random, so averaging does not remove it, and every competitor rate compared against yours inherits the same method — unfairly in favour of whoever has the more common name.

The mitigation is that verbatim answer text is stored for every successful run. The rate is a derived number; the answers are the evidence. If a brand name is a common English word, reading a handful of stored answers tells you within minutes whether the number measures the brand or the dictionary.

Reading a movement honestly

Models are non-deterministic: the same prompt asked twice can return different answers naming different brands. Sampling is the only defence, and Attensira documents one draw per prompt per model per reading on Starter and three on Growth and Business. At n=1, most week-to-week wobble sits under the noise floor.

Gating is the second defence. Every delta is tested with a two-proportion z-test at 95% significance, and a movement that fails returns {real: false, value: null} — meaning the change could not be proven, never that it was zero. A tool that instead prints every wobble as a trend is selling a story the sample does not support.

Failure modes

  • Quoting the percentage without `n`. At three draws, one hit and two hits are adjacent outcomes, and a single different answer moves between them.
  • Treating today as a full day. Each prompt × model × country combination runs at most once per workspace-local day, so today is partial until it closes. Compare whole days to whole days.
  • Reading a rate as a share of a market. It is not; see above.
  • Calling a rate a probability. It describes runs that happened on prompts you chose. See citation probability.
  • Comparing rates measured on different prompt sets. Editing prompts mid-window changes what the denominator means, and no downstream test repairs that.

Frequently asked questions

What is the denominator?

Successful runs in the window, reported with the rate as {value, n}.

Is a measured zero the same as null?

No. Null means not measured; a zero with n greater than zero means runs happened and none named the brand.

Do competitor rates sum to the whole?

No. They share a denominator and are independent, so one answer can raise several at once.

Does it predict future mentions?

No. It is an observed frequency, and Attensira computes no predicted probability, visibility score or sentiment metric.

Frequently Asked Questions about Reference rate

Successful runs in the window. In Attensira the rate is the share of completed runs whose answer text contained the brand name or domain, and it is reported alongside its sample size as {value, n}. Failed runs are stored but excluded from n, so a collection problem shrinks the sample rather than depressing the rate.

No. Attensira's documentation states competitor rates use the same denominator as yours, so they are independent rates rather than slices of a pie. One answer naming you and three competitors raises four rates at once, and their sum can exceed the whole, which makes it meaningless.

No, and conflating them invents a failure. A value of null means not measured — nothing was observed. A value of 0 with n greater than 0 means measured zero: runs happened and none named the brand. A model marked tracked:false was never queried at all.

Larger than the movement you want to claim. Attensira's documented sampling is one draw per prompt per model per reading on the entry plan and three on higher plans, and its docs point out that a one-in-three rate at n=3 moves to none-in-three or two-in-three on a single different answer. Read n before quoting the percentage.

No. It is a backward-looking frequency over prompts someone chose. Attensira computes no predicted probability, no visibility score and no sentiment metric; changes are only called real once a two-proportion z-test clears 95% significance, and a movement that fails that test is reported as unproven, not as zero.
Share this term

Track how your brand shows up in ChatGPT, Claude, and Google AI

Attensira monitors your visibility across AI search platforms so you know exactly when and how you're being recommended.