Updated 2026-09-24 · 3 min read
Almost everything written about AI assistants is a promise. This is a measurement: a median of 3 seconds, a 90th percentile of 5 seconds and 99% of replies under a minute, across 1,122 responses to messages from real clients in two salons over roughly a month.
Below is how it was measured, why the number is conservative, and the test you can run yourself in any demo to check it.
What exactly was measured
For every incoming message from a client, the time until ClaudIA's next reply in that same conversation. In customer service it's called *first response time*, and it's the standard metric precisely because it's the one the person writing notices.
| Metric | Salon A | Salon B | Together |
|---|---|---|---|
| Responses measured | 840 | 282 | 1,122 |
| Median | 3 s | 3 s | 3 s |
| 90th percentile | 5 s | 4 s | 5 s |
| Under 60 s | 99% | 100% | 99% |
Both salons give the same number, which is the first sign that we aren't looking at a fluke in one odd case.
How it was counted
Only ClaudIA's replies. When the owner answers from the panel or from her own phone, that message is tagged with its author in the database and stays out of the calculation: the number belongs to the assistant, not to the salon.
The reply to what the client has just written. Something sent more than an hour later — a reminder, an invitation to come back, a thread picked up the next day — is a different thing and is measured separately.
Everything else, in full. Every conversation of the month, without picking the good ones or removing the slow ones.
Why the number is conservative
When ClaudIA sends two or three messages in a row in reply to a single one from the client, the calculation counts all three — and the second and third arrive, by definition, later than the first.
In other words: the real first reply arrives even faster than 3 seconds. We publish the number that comes out of the raw measurement, untuned, because a figure that gets better when somebody audits it is the one worth showing.
Fast, and with the calendar in front of her
Three seconds are worth what arrives in them. ClaudIA replies having checked the real calendar: the services, each professional's hours and the slots that genuinely exist. That's why the reply isn't a menu of options but a specific time the client can book in that very message.
In practice, half the replies arrive in under 3 seconds and practically all of them within a minute.
What it compares against
Against what a salon without an assistant has today: the phone ringing seven times while somebody's hands are in a colour, and the WhatsApp that gets answered at nine at night, when the client has already booked somewhere else.
That's the comparison that counts for a salon: every minute without a reply is a client who may be writing to somebody else, and with ClaudIA the reply arrives before she has time to look.
How to check it yourself
If you're evaluating any assistant — ours or anybody else's — this is the test you can run in a demo without depending on what you're told:
1. Write the way a client would, in normal language and with a typo in it.
2. Watch the clock until the reply arrives.
3. And above all: ask for a time you know is already booked and see whether it offers it to you.
Step 3 is the one that separates an assistant from an answering machine with good manners. With ClaudIA, what arrives in those 3 seconds is a time that exists.