The SmallOffice Brief Subscribe
Scheduling & Admin
Fri, Oct 30, 2026
Admin

Missed calls: 41% to 6%

A plumbing and heating firm in Kent has three engineers and one office manager. The firm missed about four in ten calls, and each call can be worth a 180-pound job. A consultant set up an AI voice agent on the firm's real line, linked to its booking calendar. The setup used a script for the eight most common call reasons and three months of call recordings, so the agent learned real customer phrasing. Booking confirmations go out by text. Any call that mentions no heating, a leak, a smell of gas, or an elderly relative goes straight to a person within one ring. The team tested the agent for two days with difficult test calls before any real call came in.

How it wentAfter 30 days and about 190 calls, the missed-call rate fell from 41% to 6%. The agent booked 58% of all calls with no human help, and it passed 22% to a person by its own flags. Bookings that would have gone to voicemail brought about 2,100 pounds in the month, against a bill of 337.90 pounds. On day nine, a distressed elderly caller got polite questions instead of a fast transfer. She hung up and called back annoyed, and the trigger words were fixed after that call.
Try it · based on the source's workflow
Answer calls for [business name] using this script for the [number] most common call reasons: [list]. Book jobs into [calendar] and send an SMS confirmation to each caller. If a caller mentions [emergency words: no heating, leak, smell of gas], or sounds distressed, or asks for a person, transfer to [staff number] within one ring. Never quote a price outside [price list]. Send me a daily list of calls, bookings, and transfers.
A starting template based on the workflow the source describes. Review it before you use it; you are responsible for what it does.
Source: Lilach Bullock (owner's own site) · Topic: Scheduling & Admin · Tool: not named in the source · Other or custom cases
ShareXLinkedInForward to a friend
Cite this caseMissed calls: 41% to 6%. The SmallOffice Brief, Fri, Oct 30, 2026. https://smalloffice.space/case-missed-calls-41-to-6
Share this win
Missed calls: 41% to 6% — from The SmallOffice Brief, a daily brief of real AI cases for small businesses: https://smalloffice.space/case-missed-calls-41-to-6
One bot, one job

Start with one job only. Fill in the three lines. Keep the bot on that job.

The one job this bot does: ______________________________

What it may do on its own: ______________________________

What it must ask me first: ______________________________

Before and after

Two lines from this case, side by side. No new figures.

Before · as the case describes it

A plumbing and heating firm in Kent has three engineers and one office manager. The firm missed about four in ten calls, and each call can be worth a 180-pound job. A consultant set up an AI voice agent on the firm's real line, linked to its booking calendar. The setup used a script for the eight most common call reasons and three months of call recordings, so the agent learned real customer phrasing. Booking confirmations go out by text. Any call that mentions no heating, a leak, a smell of gas, or an elderly relative goes straight to a person within one ring. The team tested the agent for two days with difficult test calls before any real call came in.

After · as the source reports it

After 30 days and about 190 calls, the missed-call rate fell from 41% to 6%. The agent booked 58% of all calls with no human help, and it passed 22% to a person by its own flags. Bookings that would have gone to voicemail brought about 2,100 pounds in the month, against a bill of 337.90 pounds. On day nine, a distressed elderly caller got polite questions instead of a fast transfer. She hung up and called back annoyed, and the trigger words were fixed after that call.

The after line is the source's claim, not our measurement.

smalloffice.space · Get a case like this in your inbox each morning. Subscribe free

Send this case to my inbox

Read this case on your phone now, and keep it for later. Type your email. We send this case to that address, and you get the next cases each morning too.

Additional Details

Published: Fri, Oct 30, 2026 · Updated: Fri, Oct 30, 2026 · Topic: Scheduling & Admin · Tool: not named in the source · Other or custom cases · Source: Lilach Bullock (owner's own site)
Next case: 78% of invoices, no human input. Get cases like this in your inbox each morning.
5 cases in your inbox each morningSubscribe free