The SmallOffice Brief Subscribe
Customer Service
Tue, Nov 17, 2026
SalesBot

70% of tickets, closed with drafts

A Swedish brand sells consumer hardware direct to customers on Shopify. A small support team handles every conversation in Zendesk. Each ticket now runs a fixed pipeline. The system reads the live Shopify order and shipment data. It reads the written policy for that request type. It drafts a reply from those facts only. A separate checker pass tests every claim in the draft against the sources. A failed draft goes back for a bounded retry. A person approves the final draft in Zendesk before it sends. Nothing reaches a customer without that approval.

How it wentIn the pilot, 70% of incoming tickets closed with the pipeline draft as the reply, approved with or without light edits. The AI cost averaged about €0.30 per ticket across all model calls. The cost per resolved ticket was about €0.43. The other 30% stayed human work: complaints, disputes, request types the policy does not cover, missing data, or drafts the checker would not pass. The brand is not named, and the source calls the pilot a draft-only test, not a controlled trial. The source says the written support policy mattered more than the prompt: where the policy was vague, the drafts were vague.
Try it · based on the source's workflow
For every new [Zendesk] ticket for [store], pull the live [Shopify] order and shipment data and the written policy for that request type. Draft a reply from those facts only. Run a separate check pass that tests every claim in the draft against the order data and the policy. If the check fails, retry once, then drop the draft to me for approval. Never send a reply to a customer without a person approving it first.
A starting template based on the workflow the source describes. Review it before you use it; you are responsible for what it does.
Source: PandoraBot · Topic: Customer Service · Tool: SalesBot
ShareXLinkedInForward to a friend
Cite this case70% of tickets, closed with drafts. The SmallOffice Brief, Tue, Nov 17, 2026. https://smalloffice.space/case-70-of-tickets-closed-with-drafts
Share this win
70% of tickets, closed with drafts — from The SmallOffice Brief, a daily brief of real AI cases for small businesses: https://smalloffice.space/case-70-of-tickets-closed-with-drafts
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 Swedish brand sells consumer hardware direct to customers on Shopify. A small support team handles every conversation in Zendesk. Each ticket now runs a fixed pipeline. The system reads the live Shopify order and shipment data. It reads the written policy for that request type. It drafts a reply from those facts only. A separate checker pass tests every claim in the draft against the sources. A failed draft goes back for a bounded retry. A person approves the final draft in Zendesk before it sends. Nothing reaches a customer without that approval.

After · as the source reports it

In the pilot, 70% of incoming tickets closed with the pipeline draft as the reply, approved with or without light edits. The AI cost averaged about €0.30 per ticket across all model calls. The cost per resolved ticket was about €0.43. The other 30% stayed human work: complaints, disputes, request types the policy does not cover, missing data, or drafts the checker would not pass. The brand is not named, and the source calls the pilot a draft-only test, not a controlled trial. The source says the written support policy mattered more than the prompt: where the policy was vague, the drafts were vague.

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: Tue, Nov 17, 2026 · Updated: Tue, Nov 17, 2026 · Topic: Customer Service · Tool: SalesBot · Source: PandoraBot
Next case: No-shows: 38% down to 11%. Get cases like this in your inbox each morning.
5 cases in your inbox each morningSubscribe free