Customer Service Automation for Fashion Stores
The question a fashion store gets more than any other is “will this fit me”. It comes in a hundred forms, from a shopper who is one tap from buying, and the answer is already in the store’s own product data. Most stores answer it by hand, late, or not at all.
This page is for online fashion stores anywhere. It starts with the six workflows worth automating first, each linked to its own page with a description you can paste into AeroChat. Then it covers the messages that arrive, the channels shoppers use, the public data, two recipes you can copy in today, and the plan a store of your size typically fits.
Workflows you can automate
Each one links to a page with the flow, the description to paste, what to connect and what you still decide. The reasons for this order are on the ranked fashion store workflows page.
- Answer “where is my order” from your store. Checks the shopper’s email or phone first.
- Recommend a size from the product’s own chart. Says so when a product has no measurements.
- Handle returns and exchanges inside your window. Offers an exchange first, and passes damaged or wrong items to your team.
- Recommend products from your live catalogue. Only items in stock, with the product link.
- Answer stock by size and colour, and note restock requests. Offers the nearest variant that is in stock.
- Answer replies to your abandoned-cart message and close the sale. The message goes out as a WhatsApp broadcast, from the Growth plan. AeroChat answers the questions that come back.
What automation does for a fashion store
- More orders from the shoppers who ask first. A size or stock question answered in seconds, with a reason, is often the last step before checkout.
- Fewer returns from wrong sizes. A recommendation read from the product’s own size chart and fit notes is more reliable than a guess from a busy team member.
- Peak weeks stay manageable. During a drop or a sale the message mix shifts towards availability, size and delivery questions, which are exactly the ones a workflow handles from live data.
The messages a fashion store gets
| Message | How shoppers write it | What the workflow does |
|---|---|---|
| Sizing | “im 1.65m 55kg which size”, “usually M in uniqlo, same?” | Reads the product’s size chart, fit note and fabric, and recommends a size with the reason |
| Stock by variant | “do you have the black in S” | Checks live Shopify stock for that variant, offers a near variant if it is gone |
| Delivery date | “will it arrive before saturday” | Quotes shipping rates and times for the shopper’s address |
| Order status | “where is my order” | Verifies the shopper’s email or phone, then reads the order and tracking |
| Return inside the window | “can i return this, too big” | Checks the order date against your policy and explains the next step |
| Damaged, wrong item or annoyed customer | “you sent the wrong colour” | Hands to a person with the order details attached |
A sizing workflow must never invent a chart. If a product has no measurements recorded, the honest reply says so and offers a person. A confident wrong size produces a return, which costs you the margin and the shipping both ways. See AI hallucination. Stock is the same. “Do you have the black in S” needs a live inventory read, because your product page says the item exists and says nothing about the black small selling out an hour ago.
Channels shoppers use
For fashion, the Instagram direct message is the shop floor. A shopper sees a post, asks about it, and buys in that conversation or does not buy. AeroChat replies to comments on Instagram and Messenger posts as well as direct messages, so a comment saying “price?” or “size S?” opens a conversation while the shopper is still looking. See conversational selling through Instagram DMs. WhatsApp carries repeat customers and order questions. Web chat catches the shopper with your site open, often mid-checkout. AeroChat’s TikTok channel puts TikTok direct messages and TikTok Shop buyer chat in the same inbox.
The store itself runs on a platform such as Shopify or WordPress. That is where product and order data live. The channels are where customers talk to you. A workflow that answers well reads the platform and replies on the channel.
What the data says
| Figure | What it measured |
|---|---|
| 19.3% | of US online sales expected to be returned in 2025 (15.8% across all retail sales) |
| 82% | of shoppers say free returns are a major factor in deciding where to buy |
| 71% | are less likely to shop with a retailer again after a poor returns experience |
Source: National Retail Federation, 2025 Retail Returns Landscape, October 2025. Survey of 2,006 US consumers and 358 ecommerce professionals.
| Figure | What it measured |
|---|---|
| 70.22% | average documented online cart abandonment rate, across published studies |
| 72.4% | of consumers are more likely to buy from a brand that offers messaging |
Sources: Baymard Institute, cart abandonment rate statistics, updated September 2025. Meta, State of Business Messaging, Kantar survey of 11,056 adults in 22 markets commissioned by Meta, which owns WhatsApp, 2025.
The returns figures are from the US, where data is best published. They show why sizing is worth automating carefully: each avoidable return costs shipping twice and some of the customer’s goodwill.
Recipe: sizing and stock
Paste this into AeroChat (Skills, then Build from a description) and change the example values to yours.
Copy this into AeroChat
When a shopper asks which size to buy, follow these steps.
- Ask for their height, weight and the size they usually wear, if they have not said.
- Read the size chart, fit note and fabric for that exact product and recommend one size with the reason, for example: “For 1.65m and 55kg the M fits with room. This style runs slightly small in the shoulders, so take the L if you are between sizes.” If the product has no size chart, say so and offer to pass the question to our team.
- Check stock for that colour and size. If it is sold out, offer the closest variant that is in stock, such as the same size in another colour.
- If they ask whether it will arrive by a date, check the shipping rates for their address and tell them the delivery time, and say plainly if it will not make the date.
- When they are ready, send the product link.
Never promise a fit, and never recommend a size the chart does not support. Reply in the shopper’s language.
What to connect:
- Your store. Shopify is built in: install the AeroChat app, which syncs products, variants and stock. WordPress stores connect the same way. Size charts and fit notes should be on the product, in the description or a product field.
- Your channels. Instagram, WhatsApp and web chat. Built in.
Recipe: returns inside the window
Copy this into AeroChat
When a customer asks to return or exchange an item, look up their order after checking their email or phone number. Our return window is 14 days from delivery for unworn items with tags (example policy, change it to ours). If the order is inside the window, explain how to send it back and offer an exchange for a different size first, checking that the replacement size is in stock. If it is outside the window, the item is damaged, we sent the wrong item, or the customer is upset, do not decide anything. Collect the order number, what happened and a photo if they have one, and hand the conversation to our team with those details. Never offer a refund or discount beyond our written policy.
What to connect: your store (order lookup is built in for Shopify and WordPress), and your returns policy uploaded to the knowledge base. You set refund and discount limits in AeroChat, and anything larger goes to your team.
After you paste a recipe, AeroChat builds it as a draft with a checklist: connect your accounts, upload your lists, then switch it on. Any keys are entered in the dashboard and never pass through the conversation.
Using a different system? If it has a public API, it connects to AeroChat the same way: describe what you want, paste in its key, and it runs.
Can’t find your tool? Message us in the chat on this page and we’ll tell you how it connects.
What a store of your size typically invests
AeroChat plans are priced on AI responses, the individual replies the AI sends. A sizing conversation is usually several responses. A worked example: a store with about 30 product conversations a day, at around four replies each, uses roughly 3,600 responses a month.
- A new or small store answering a handful of questions a day usually fits Starter: 500 AI responses a month and 3 team seats.
- An established store with steady Instagram and WhatsApp traffic usually fits Growth: 2,000 AI responses a month and 10 seats, plus payment links in the chat and WhatsApp broadcasts.
- A store at the volume in the example, or one running regular drops, usually fits Advanced: 5,000 AI responses a month, 25 seats and auto-translation.
In a drop week you can top up with extra AI credit instead of moving plans. What the investment does is answer the size and stock questions while the shopper is still deciding, and keep your team for exchanges and complaints.
Try it on your own catalogue
Install AeroChat on your Shopify store, paste the sizing recipe, and ask it about your best-selling dress the way a shopper would. You will see whether your size charts are good enough before any customer does.
Related reading: AI hallucination, cart abandonment, WISMO (where is my order), payment link, conversational selling through Instagram DMs, back-in-stock alerts on WhatsApp and Instagram. All fashion store workflows. All industries.
Install AeroChat from the Shopify App Store and start your 7-day free trial.
Not on Shopify? Sign up here.