Customer service
Turn sold-out into a second chance
AI captures back-in-stock requests so the right customer hears when the item returns.
A sold-out item is a customer who wanted to buy and could not, and most will not come back to check. This workflow lets an AI agent record exactly which item, size and color they want and pass it to your restock list, so the demand you would otherwise lose is still there when the stock is.
Last reviewed
Can AI tell a shopper when a sold-out item is back?
It records the request; you send the alert when the stock lands. The agent captures exactly which item, size and color the shopper wants and puts it on your restock list, so demand you would have lost is still there when the item returns.
- Answers
- What you carry, and what sold out
- Hands over
- The item, the variant and the shopper’s details
- Not yet
- Seeing when stock actually lands
Your customers are already asking AI
These are the kinds of prompts people now type into an AI assistant — the demand this workflow is built to serve.
“tell me when this item is back in stock”
“find a shop that notifies me when products restock”
“which store can alert me when my size is available again”
“who lets me get a back-in-stock alert by text”
So how does a customer's AI find this at all?
Recovering sold-out demand only helps if shoppers reach you in the first place. Make your shop and this back-in-stock alert available to AI, so when a customer asks their assistant to be told when an item returns, AI can point them to you and capture the request.
You describe your range and how you handle restocks — and Fugentic publishes that as an MCP server: the thing that lets an AI assistant ask your shop a question and get a real answer back. It is registered from the platform, so an agent finder, the index an assistant checks to see what is available, can pick it up.
Then a shopper whose size is gone everywhere asks their assistant who can tell them when it returns — and instead of losing that person to whoever restocks first, you have their exact variant on a list with their contact details.
- 1You describe what you sell
- 2It's published and registered
- 3A customer's assistant asks
- 4It answers in your words
- 5The details reach you
What AI can and cannot do here today
What AI can do today
- It can say what you carry and which variants you normally stock.
- It can capture the exact item, size and color a shopper wants, so the request is actionable.
- It can put the request on your restock list with the shopper’s contact details attached.
What it cannot do yet
- It cannot see when stock lands. There is no live inventory feed, so you trigger the alert once the item is actually back.
- It cannot reserve the item or take payment. No orders, no holds — the shopper hears from you and buys as normal.
Everything on the left is what a text-based setup supports today. Quoting against live data, and taking the booking itself, need server types we hope to add later.
How the AI back-in-stock workflow works
- 1
Customer asks to be notified
A shopper messages about a sold-out item and asks to be told when it's back.
- 2
AI records the request
The agent notes the exact item and variant the customer wants.
- 3
Request lands on your restock list
The request goes to your team with the item and variant attached, ready for when it comes back in.
- 4
Customer hears when it returns
When you restock, the customer gets a text or email pointing them back to the item they asked about.
Tools in this workflow
These are the tools the workflow touches. Map them in the Agentic Planner to describe what your agent can do.
Shopify
Manage products, orders, customers, and inventory in your Shopify store
Twilio
Send SMS and MMS messages, initiate and monitor phone calls, look up phone number metadata, and manage Twilio messaging resources from agent workflows.
SendGrid
Send transactional emails, use dynamic templates, manage contact lists, and retrieve delivery stats from agent workflows using the SendGrid Email API.
Industries this fits
Build this workflow
Open this exact workflow in the free Agentic Planner and adapt it to your business — no code required.
Related use cases
AI review response automation
Reply to every review quickly and on-brand — without it eating your day
Answer "do you carry it" before they walk out
AI answers what you stock, in which sizes and colors, the moment a shopper asks — no hold music, no guessing.
Answer "where is my order?" instantly, every time
AI answers what your delivery promise covers, and hands the specific order to your team.
Frequently asked questions
Yes — the agent tracks the exact variant, so a customer only hears when their size is back.
As soon as you mark the item back in, so the customers who asked for it get first pick before it sells out again.
Either — the agent can alert by SMS, email, or both, depending on what the customer prefers.
You describe your range once, and Fugentic publishes it as an agent an assistant can ask, then registers it so an agent finder — the index an assistant checks to see what is available — can pick it up. A shopper hunting a sold-out size is asking several shops at once; being one an assistant can actually ask is the difference.
Make your services available to AI
Describe what you sell, what it costs and how you decide — then publish it as an agent an assistant can ask. No code.