Almost half of all people got no answer
The only account in the set where the full picture is measurable, booked call rate included. That is why it comes first.
Calls booked per month
108.7
326 in the last 90 daysAverage over the last 90 days, counted from bookings that carry an actual scheduled call time. No such figure exists for the period before installation, because nobody was recording bookings then.
- People who got a reply within 24 hours53.3%96.7%
- Median time to reply2.3 h52 s
- Conversations with at least one follow-up17.6%71.1%
A mentoring account: the owner teaches people to build a business around a personal brand and sells through a call, not through a link in the bio. Every lead from the inbox has to be qualified and walked to the calendar, which means the quality of inbox handling maps directly onto revenue.
Almost every second person writing to this account got no answer within a day. Today 96.7 percent do, at a median of 52 seconds.
The starting point: every second person left hanging
In the year before installation, 53.3 percent of the people who wrote anything in text to this account received a reply within 24 hours. This is not about individual messages but about people: almost every second one got no reaction within a day of their first message.
Those who did get an answer waited a median of 2.3 hours for it, and one in ten waited over 18 hours. Outside working hours the median rose to 2.4 hours. Follow-up barely existed: only 17.6 percent of conversations received a single reminder, which works out to 0.3 per conversation.
What the measurement showed afterwards
Today 96.7 percent of people get a reply within 24 hours. It is not zero and never will be: some conversations are taken over by a human who then does not finish them, some leads are deliberately filtered out, and the agent intentionally ignores certain kinds of prompts. But the difference between every second person and nineteen in twenty is the whole content of this case.
Median reply time fell to 52 seconds and the ninetieth percentile to 1.7 minutes, so the tail of the distribution disappeared. Outside working hours the median is 51 seconds, exactly the same as midday. Follow-up reached 71.1 percent of conversations instead of 17.6, at 1.3 reminders per conversation.
The end of the funnel: booked call rate
Reply time on its own interests nobody. The outcome does, so we counted it separately. The classifier read 1,301 conversations from the before window and 1,500 from the after window, applying the same measure to both. It found 56 booked calls before installation and 100 after, which is 4.3 percent against 6.7 percent.
The difference is statistically significant: a two proportion test gives p below 0.01. The 95 percent confidence intervals touch at the boundary, 3.3 to 5.5 percent before and 5.5 to 8 percent after, so this is a real effect rather than a tenfold miracle. The honest version of this sentence is: on this account the booking rate grew by half.
Why this is not one hundred percent
Two groups are left without a reply, both of them on purpose. The first is friends and accounts the client themselves follows: the tool has a setting to leave them alone, because nobody wants an agent pitching their mates. The second is contacts rejected immediately against the disqualification criteria the client sets. On top of that there are conversations a human took over and never finished. One hundred percent on this metric would mean the tool answers everybody indiscriminately, and that is a defect rather than a feature.
Every metric we measured
The full table, including the metrics that did not improve. Sample sizes sit below it.
| Change | Year before Setor | Last 90 days | Change |
|---|---|---|---|
| People who got a reply within 24 hours | 53.3% | 96.7% | 43.4 pp |
| Median time to reply | 2.3 h | 52 s | 158× faster |
| Conversations with at least one follow-up | 17.6% | 71.1% | 53.5 pp |
| Booked call rate | 4.3% | 6.7% | 2.4 pp |
| Median reply outside working hours | 2.4 h | 51 s | 170× faster |
| Ninetieth percentile time to reply | 18.2 h | 1.7 min | 653× faster |
| Replies within 5 minutes | 22.2% | 97% | 74.8 pp |
| Follow-ups per conversation | 0.3 | 1.3 | 4.3× more |
| Conversations held | 1,479 | 5,462 | 3.7× more |
What each of these numbers actually measures
- People who got a reply within 24 hours
- Share of conversations where a person wrote something in text and received a reply within 24 hours of their first message. It counts people, not messages.
- Median time to reply
- The middle of the distribution of time between a lead's message and the business reply that follows it. Pairs longer than 24 hours are dropped, because that is a follow-up.
- Conversations with at least one follow-up
- Share of threads in the window where the business wrote again after at least thirty minutes without a reply. The denominator is every thread, single-message ones included, so the figure is understated on both sides of the comparison.
- Booked call rate
- Share of classified conversations whose content indicates a call was booked.
- Median reply outside working hours
- The same figure, computed only for messages outside Monday to Friday 9:00 to 17:00, in the seller's timezone.
- Ninetieth percentile time to reply
- The boundary of the slowest tenth of replies: nine in ten arrive faster than this.
- Replies within 5 minutes
- Share of pairs where the reply arrived within five minutes.
- Follow-ups per conversation
- Average number of such reminders per thread.
- Conversations held
- Conversations in the window with at least three messages where both sides spoke.
What these numbers rest on
Before window
January 2025 → January 2026
1,479 conversations in window
3,790 reply pairs
After window
Last 90 days
5,462 conversations in window
28,644 reply pairs
Cutoff point
January 9, 2026
The first trace of Setor on this account.
A conversation counts when the lead wrote something in text. That is the denominator for every percentage on this page apart from the time based metrics. A pair is a lead's message and the business reply that follows it. That is the denominator for the time based metrics.
How we counted thisSee the report on 1.58 million messagesHigh-ticket sales on Instagram
Want to see these numbers on your own account?
On the call we go through your inbox and show you how many messages currently go unanswered.