# A shopper’s sizing worry becomes a typed record before checkout.

You reduce ecommerce returns by asking the fit question before checkout instead of after. A conversational agent asks what someone usually wears, in their own words, types the answer into a structured fit record, and posts it to your stack, so the mismatch that would have shipped and come back gets caught first.

## The process this page is about

Not "AI for ecommerce". One moment: the point where a shopper’s doubt about size, about what arrived, or about whether to keep it, either gets asked one good question or gets a dropdown that does not fit the sentence they actually wanted to type.

- **Who starts it**: Someone staring at a size chart with no confidence, or someone holding a box that is not what they ordered. Almost always mid-checkout or mid-unbox, rarely during a quiet moment.
- **What it costs today**: A static size chart nobody trusts, so shoppers order two sizes and return one. A returns portal with six reason-code dropdowns and no room for "it fits like a size down". A wholesale inbox where one real buyer sits next to a hundred spam pitches.
- **What it has to produce**: A typed record: the item, the fit or the fault, what the customer actually wants done about it, and whether anything about it needs a person right now rather than a form.
- **of fashion returns come down to size or fit, and a static chart never asks the question that would have caught it**: 70% (source: FitEz)

## What it asks, and what it never asks

You name the fields your store already tracks. It does the asking, in whatever order the story comes out, and it keeps asking until the required ones are filled.

| Field | Type | Required | Why |
|---|---|---|---|
| item_of_interest | text | yes | Anchors the fit note to the right product |
| usual_size_other_brands | text | yes | Calibrates the recommendation to how they actually fit, not a chart |
| fit_preference | text | yes | Relaxed, true-to-size or fitted, in their own words |
| order_number | text | yes | Ties every return, exchange or report back to the order |
| return_reason | text | yes | Routes the return and flags a defect pattern early |
| desired_size_or_color | text | yes | What the swap should actually deliver |
| safety_or_allergen_concern | boolean | yes | The one answer that triggers the hard stop to a human |
| business_type | text | yes | Sorts a wholesale lead before anyone quotes a price |
| product_categories_interested | list | yes | What the wholesale team should actually pitch |
| would_reorder | boolean | yes | The honest signal a review widget never asks for |

### And what it will not do

- It never authorises, approves or promises a refund, credit or exchange itself. The team reviews and confirms.
- It never promises or estimates a delivery date, shipping window or restock date. The fulfillment team confirms timing.
- It never confirms or guesses current stock, size or color availability. It cannot see live inventory, so it says the team checks before anything ships.
- It never quotes a wholesale price, a discount tier or a minimum order quantity.
- The moment a detail sounds like a safety or allergy concern, it stops asking questions and says a person is being notified right now.
- It never invents a field. If the customer did not say it, the record says "Not captured" instead of a guess.

## Try the run yourself

Six situations a store actually handles, each running its own agent with its own fields. The obvious seventh, "where is my order", is not here on purpose: it is not a lead, and every ecommerce demo on the internet already shows it. Pick one and answer it the way a real customer would, out of order and mid-thought.

- [Not sure which size to order](https://joina.chat/l/fg-size): Chat widget. The pre-purchase fit check, in the corner of your product pages.
- [The box has the wrong thing in it](https://joina.chat/l/fg-wrongitem): Conversation page. A shipping-error report with a hard stop for anything unsafe.
- [Do you do wholesale](https://joina.chat/l/fg-wholesale): Conversation page. A shop qualified before anyone quotes a price.
- [I want to send this back](https://joina.chat/l/fg-return): Conversation page. A reason and an outcome, no dropdown required.
- [Can I swap it for a different size](https://joina.chat/l/fg-exchange): Conversation page. A straight exchange, not a complaint.
- [How did the order go](https://joina.chat/l/fg-feedback): Conversation page. Honest feedback on a completed order, not a lead.

## Frequently asked questions

**What does Gnosari do for an online store?**

Gnosari runs the conversations an online store handles today with a size chart, a return form and a wholesale enquiry page: what a shopper usually wears before they buy, what actually went wrong when they send something back, and how big a trade order would be. It asks one question at a time on your site, then posts a typed record to your store, helpdesk or sheet, so your team acts on data instead of a free-text box.

**How do I reduce returns caused by wrong sizes and vague return reasons?**

Create a free Gnosari account and tell it which fields your size guide and return form already try to capture: usual size and brand, fit preference, the item and order number, the reason in the shopper's own words. Embed it on the product and returns pages. Gnosari asks one question at a time, follows up on a vague reason, and posts the record to Shopify or BigCommerce through a webhook, Zapier or Make. You see why items come back, per SKU.

**Will Gnosari confirm stock, quote a price or promise a delivery date?**

No. Gnosari is instructed never to confirm or guess current stock, size or colour availability, never to quote a price or a discount, and never to promise or estimate a delivery, shipping or restock date. It says plainly that the team checks and confirms, which is the honest answer while it cannot see live inventory. If a detail sounds like a safety or allergy concern, it stops collecting fields and says a person is being notified.

**Does Gnosari approve a refund or qualify a wholesale buyer on its own?**

Neither. Gnosari records what a customer wants, the reason and the item condition, but never authorises, approves or promises a refund, credit or exchange: that decision stays with your team. For wholesale, it asks about the business, the expected order volume and the resale certificate, but never quotes a wholesale price, a discount tier or a minimum order. It says the wholesale team reviews the fit and follows up with pricing.

**Does Gnosari work with Shopify or BigCommerce?**

Yes, through a webhook. The moment a record is complete, Gnosari posts a signed JSON payload to the address you give it, and Zapier or Make routes it into Shopify, BigCommerce, your helpdesk or a sheet. There is no Gnosari app to install on either side, and the record is already in your Gnosari inbox before delivery starts, so a down endpoint never loses a return or a wholesale lead.

## Five minutes from now your size and return questions could be answering themselves.

Build the agent, put it on your product pages, and watch the first fit record arrive. Free to start, no card.

Full page: https://gnosari.com/for/ecommerce