Skip to content

How Massyl measures

AI answers change from one ask to the next. The same question can name your brand on Monday and leave it out on Tuesday. So Massyl never judges from a single answer. It measures rates over many answers and shows how sure each rate is.

20 answers per question, per engine, per month

Section titled “20 answers per question, per engine, per month”

Each question you track is asked 20 times per engine per month. The asks are spread across the weeks, so one unusual day or one model update does not dominate the result.

From those answers Massyl counts how often your brand is named. That count, divided by the number of answers, is your mention rate.

A rate from 20 answers is an estimate. Massyl shows each rate with a 95% range, computed with the Wilson score interval, a standard method for rates.

In plain words, the range is the span the true rate very likely falls in, given the answers so far. A narrow range means you can act on the number. A wide range means you should wait.

Here is how the range shrinks as answers add up, for a brand whose true rate is about 40%:

Answers 95% range
1 0% to 79%
5 12% to 77%
10 17% to 69%
20 22% to 61%
50 28% to 54%
100 31% to 50%

One answer tells you almost nothing. Twenty answers tell you roughly where you stand.

When a range is too wide to act on, Massyl says “Not enough data” instead of showing a number. We would rather tell you we do not know yet than show a figure that might send you in the wrong direction.

Sometimes the picture is clear quickly. If a brand is named in nearly every answer, or in none, a few answers may already give a narrow range. In that case Massyl can stop early for that question and use the remaining checks where the picture is still unclear.

One question with 20 answers gives a wide range. Your overall visibility combines many questions, so the answers add up.

For example, 24 questions x 20 answers = 480 answers. With a true rate of about 40%, the overall range narrows to about 36% to 44%. That is precise enough to compare month to month.

Massyl shows both levels:

  • Per question, to see where you are strong or weak
  • Overall, to track your visibility over time

Answers drift even when you change nothing. To tell a real gain from drift, Massyl holds some questions back untouched as a control group. It reports the gain of your changed pages over the control, with its own range. If the ranges overlap, it says the change is not proven yet. See fixes and publishing.

Each answer is stored with its date, engine, country and language, plus a link you can share. You can always open the answers behind a number and read them yourself.

For a longer explanation, read One AI answer is a coin toss, not a measurement.