The SmallOffice Brief Subscribe
Sales & Leads
Sun, Nov 15, 2026
Sales

214 messages sorted, 61 flagged

Lilach Bullock runs a five-person business. An agent reads every new message from LinkedIn, website forms, and email, and checks each one against written rules: does it name a service, name a budget, and come from a company domain? It drafts a reply for messages worth answering, tags the rest, and logs each one in Airtable with a summary line. It sends nothing. A person clicks approve first.

How it wentOver four weeks the agent did the first pass on 214 messages and flagged 61 for a human reply. Assistant time fell from about 45 minutes a day sorting to about 8 minutes a day checking, about 14 hours saved in a month. Catch, from the owner: it once drafted a reply with an old price from a page pulled in weeks earlier, and only the approval step caught it.
Try it · based on the source's workflow
Do the first pass on new messages for [business name] from [inbox and forms]. Check each message against these rules: [names a service we sell, names a budget, comes from a company domain]. For messages that pass, draft a reply in my voice from [examples] and use only the current prices in [price document]. Tag the rest by reason. Log every message in [CRM] with a one-line summary. Do not send anything: show me the drafts and the flagged list for approval.
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 · Topic: Sales & Leads · Tool: not named in the source · Other or custom cases
ShareXLinkedInForward to a friend
Cite this case214 messages sorted, 61 flagged. The SmallOffice Brief, Sun, Nov 15, 2026. https://smalloffice.space/case-214-messages-sorted-61-flagged
Share this win
214 messages sorted, 61 flagged — from The SmallOffice Brief, a daily brief of real AI cases for small businesses: https://smalloffice.space/case-214-messages-sorted-61-flagged
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

Lilach Bullock runs a five-person business. An agent reads every new message from LinkedIn, website forms, and email, and checks each one against written rules: does it name a service, name a budget, and come from a company domain? It drafts a reply for messages worth answering, tags the rest, and logs each one in Airtable with a summary line. It sends nothing. A person clicks approve first.

After · as the source reports it

Over four weeks the agent did the first pass on 214 messages and flagged 61 for a human reply. Assistant time fell from about 45 minutes a day sorting to about 8 minutes a day checking, about 14 hours saved in a month. Catch, from the owner: it once drafted a reply with an old price from a page pulled in weeks earlier, and only the approval step caught it.

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: Sun, Nov 15, 2026 · Updated: Sun, Nov 15, 2026 · Topic: Sales & Leads · Tool: not named in the source · Other or custom cases · Source: Lilach Bullock
Next case: $500 a week, not binned. Get cases like this in your inbox each morning.
5 cases in your inbox each morningSubscribe free