Photo capture on a phone
An installable app: snap one or several photos, or upload them. A background queue processes the items, and it survives a refresh or a weak signal, so a batch can be shot in the stockroom and left to run.
For shops that list lots of unique items: take a photo, and the system identifies the item, drafts the title and description, picks a category and condition, researches comparable prices and suggests one. Staff review every draft before it goes live. It’s AI automation aimed at the slowest job in the shop.
A second-hand shop, an antiques dealer or a vintage seller has to identify every item, write a description, find a comparable price and photograph it. For a unique piece there is no supplier data to import, so each listing is built from scratch. A hundred items is a week of work before the first sale. The photographing is the quick part. The research and the typing are what slow you down.
Pick the ones you need. Each is built around how your team already works, then joined up on one set of data.
An installable app: snap one or several photos, or upload them. A background queue processes the items, and it survives a refresh or a weak signal, so a batch can be shot in the stockroom and left to run.
An image search service identifies what the item is, with brand and model where it can, as the starting point for the draft.
An AI model writes the title, description, brand, model, category and condition in your house style, using what it found and your category rules.
Comparable items are searched, EU listings first, and a price is suggested from what similar items are listed for, with the source shown so you can judge it.
Staff see the photo, the draft, the suggested price and where it came from, answer a short questionnaire per category (size, defects, authenticity notes) and approve. Nothing is published unprompted.
Approved listings are saved to your own catalogue and storefront, or pushed as products to Shopify or WooCommerce through their APIs.
An existing stock spreadsheet and photo folders can be imported from Google Drive, so the tool starts with your current items, not an empty shop.
Every draft and edit is logged, and you can set what the AI may fill in on its own and what always needs a person.
The same five steps on every project, sized to yours.
Tell me how the business runs today: the tools, the workarounds, the bit that drives you mad. The quote builder takes about five minutes and gives me a scoped brief.
I reply with a fixed price and a phase plan. The must-haves go first, so you are using the system while the rest is still being built.
You see the real system on a private link while it is being built, with your own data in it as early as possible. Changes are cheap at this stage, so this is where we make them.
Spreadsheets, an old system, email threads: the data comes with you, checked against the source so nothing is lost on the way.
Your team gets a walkthrough, and I stay on for fixes and new features, either on a monthly support plan or pay as you go.
No. It drafts and suggests; a member of staff reviews and approves each listing. You can decide which fields it fills in and which always need a person.
It’s a starting point drawn from comparable listings, with the source visible. For ordinary goods it gets you close quickly; for rare or valuable items a person must decide. The review screen exists so that judgement stays with staff.
Business API access from the major providers isn’t used to train their models by default. I build on those APIs and keep your data in your own systems; the details for your provider are set out in the proposal.
Yes. Approved listings can be created as products in Shopify or WooCommerce through their APIs, or kept in a catalogue of their own. See Shopify stock sync for keeping the stock in step after that.
A short pilot on one category is typically a matter of weeks, and tells you whether the drafts and prices are good enough before you scale it up. AI and automations is roughly 35 to 90 build hours, plus 30 to 50 hours of shared groundwork.
Then the reviewer corrects it before publishing, which takes seconds on the review screen. The draft shows what the system found and where the price came from, so a wrong identification is easy to spot. Over a batch, the time saved on the ones it gets right pays for the ones it doesn’t.
Agents that sort email, draft replies, read documents and update records, with approval.
IndustryRetail & e-commerceStock across shop and online, orders, suppliers and fast AI-assisted listing.
SystemInventory managementStock across shop, stockroom and online, with variants, barcodes, supplier reorders and stock takes.
SystemShopify stock syncTwo-way Shopify stock and order sync with your shop, reconciliation and alerts when they disagree.
Case studySecondhand MaltaPhotograph an item, get a listing: an AI scanner that writes the copy and researches the price.
IntegrationShopifyShopify orders, stock and customers synced with a custom back office or ERP.
GuideHow to write a software briefA one-page brief for a custom system, with a checklist, so quotes arrive comparable.
Agents that sort email, draft replies, read documents and update records, with approval.
Retail & e-commerceStock across shop and online, orders, suppliers and fast AI-assisted listing.
IntegrationsWix, Shopify, Gmail, WhatsApp, Stripe, calendars and accounts, synced both ways.
Custom ERPQuotes, stock, staff, jobs and invoicing on one shared set of data.
How pricing works · Digitalise Your SME grants · All case studies
The quote builder opens with the parts on this page already switched on. Add or remove what you like, and I reply with a fixed quote.