Skip to content
Ecommerce AI agent

An ecommerce AI agent that shops your catalogue and fills the basket.

It reads what a shopper wants, searches your live catalogue, checks the results and builds the basket. The shopper confirms before anything is ordered.
A father and child in front of a phone shaped like a grocery shelf
In short

Updated

An ecommerce AI agent is software that shops a store's catalogue for a customer: it searches, checks what it found, adds to the basket and prepares the checkout.

Read moreShow less

An ecommerce AI agent is software that shops a store's catalogue for a customer: it searches, checks what it found, adds to the basket and prepares the checkout. bisky is an ecommerce agent for supermarkets, grocery delivery and quick commerce.

It works inside the retailer's own app and website and on its WhatsApp Business number, typed or by voice, in Arabic and English, and it never places an order without the shopper's confirmation.

What is an ecommerce AI agent?

An ecommerce agent is the difference between being told where the milk is and having it put in your basket.

Three kinds of AI for ecommerce, by what they do.

ChatbotSite searchEcommerce AI agent
What it doesAnswers questionsRanks results for a typed querySearches, checks, adds to the basket, builds the checkout
What it readsHelp-centre articles, scripted flowsThe catalogue indexThe live catalogue, the shopper's branch, the basket
Input it handles bestCommon questionsShort keywordsSentences: lists, budgets, recipes, follow-ups
Changes the basketRarelyNoYes, and only orders after the shopper confirms
Read moreShow less

An ecommerce agent is the difference between being told where the milk is and having it put in your basket. Three kinds of software get called "AI for ecommerce", and they do different jobs.

A chatbot answers questions. It is usually trained on help-centre pages and scripted flows: opening hours, delivery fees, return policy. It talks, it does not shop.

Site search ranks products for what a shopper types in the search bar. It is fast and essential, and it is built for short keywords. "Snacks for six people watching the game under 20 dollars" is not a keyword.

An ecommerce AI agent uses tools. It searches the live catalogue with the shopper's branch prices and stock, checks that what it found matches the request, adds products to the basket, changes quantities and builds a checkout. This is what people mean by agentic shopping: the agent does the legwork, and the shopper approves the result.

What should an ecommerce agent automate first?

In grocery, start with the requests that are slow for shoppers and that a search bar handles badly.

Search in shoppers' words

Requests as people write them: Arabic, Arabizi, English, misspelled, mixed.

Details

"7aleeb" finds milk.

Lists in one message

"Milk, bread and eggs" returns a row per item, so the shopper picks each without asking three times.

Recipes to baskets

A dish and a number of people becomes ingredient lines, the right packs and one tap to add them all.

Budgets and cheapest

"Under $20" and "cheapest first" are understood and held for follow-ups.

Orders on WhatsApp

Product cards, a basket and a checkout the shopper confirms with a tap on your own number.

Orders by voice

A shopper orders on a WhatsApp call or a voice call inside your app.

Details

The basket is read back and the keypad confirms.

Read moreShow less

Grocery baskets are long, repeat often and depend on details a search bar ignores: pack sizes, the branch that will deliver, budgets, and what a family is cooking tonight. Those are the requests where an agent saves the most time, because each one would otherwise take several searches and taps.

Leave to people what needs judgement or authority: complaints, a late or wrong delivery, refunds, a large catering order, anything to do with an account or a payment dispute. The assistant can recognise these and hand the conversation to your team, who see it in the same inbox with everything said so far. A shopper can ask for a person at any time.

How does it act safely?

An agent that can change a basket needs harder limits than a chatbot that only talks.

  • The shopper confirms every orderNo tool the model can call places an order.
  • Your rules are enforced on the serverA retailer can hide alcohol, pork and tobacco, or all three for a halal store.
  • It is tested on your catalogue firstBefore launch, and before any change to the prompt, the model or search goes live.
  • Off-topic results are droppedEvery search's top results are checked against the shopper's actual message before they are shown.
Read moreShow less

An agent that can change a basket needs harder limits than a chatbot that only talks. bisky puts them in the server, not only in the instructions to the model, so no wording from a shopper can talk its way past them.

The shopper confirms every order

No tool the model can call places an order. The agent fills the basket, in sync with your app's cart, and builds a checkout. The order is placed only by the shopper's explicit confirmation: a tap on WhatsApp, a signed checkout page, or pressing 1 on the keypad after the basket is read back on a call. A typed or spoken "yes" alone never places an order. The order then goes to your platform through its connector, to your orders API, or to your team as an order ticket.

Your rules are enforced on the server

A retailer can hide alcohol, pork and tobacco, or all three for a halal store. Those products are removed by the server before the agent sees the catalogue, on every channel. Each product is judged by an AI model, not a word list, and a product that has not been checked yet stays hidden. Out-of-stock products cannot be added, and prices and stock come from the shopper's own branch.

It is tested on your catalogue first

Before launch, and before any change to the prompt, the model or search goes live, a test suite generated from your own catalogue runs: every department covered, retrieval of real products, basket changes, the language of each reply, safety, and WhatsApp flows. Generic benchmarks say little about whether an agent finds your 1 L fresh milk when a shopper writes "7aleeb".

Off-topic results are dropped

Every search's top results are checked against the shopper's actual message before they are shown. A request for snacks for a basketball night shows snacks, not basketballs.

How do support agents, shopping agents and search engines compare?

Most retailers need more than one. This is what each kind of tool is built for, stated generally.

Categories of tool compared by their core job. Many tools now add AI features beyond it, so check the current features of any you consider.

Support agentsShopping agents (such as bisky)Search engines
Main jobResolve customer service questions and ticketsTurn a shopper's request into a basketRank products in the search bar and category pages
Typical questionsWhere is my order? Can I return this?Kabsa for 6. Cheapest milk. Snacks under $20.A typed keyword: milk, rice, shampoo
Works fromHelp centre, policies, order data, ticketsLive catalogue, branch prices and stock, basketCatalogue index, behaviour data, merchandising rules
Acts on the basketUsually notYes: adds, changes quantities, builds checkoutNo, the shopper clicks
Where it livesHelp widget, email, social inboxesYour app, your website, WhatsApp, typed or by voiceYour site and app search
Where it is strongerTicketing, agent workflows, support analyticsMulti-item requests, recipes, budgets, dialects, voiceSpeed at scale, merchandising control, search analytics
Use it alongside the others?Yes, for after the orderYes, for shopping in conversationYes, for the search bar
Read moreShow less

Support agents are strong at what happens after the order: tracking questions, returns, policies, routing tickets to the right person, and reporting on support quality. If most of your chat volume is "where is my order", start there.

Search engines power the search bar and category pages at large scale, with merchandising controls and analytics a team can tune. They are the right tool for the many short queries a big store gets.

A shopping agent sits in the conversation: it takes a sentence, a voice note or a call and turns it into a basket. bisky is built for that, for grocery in particular, and for shoppers who write and speak Saudi, Gulf or Lebanese Arabic, Arabizi and English.

Where does the agent live?

Shoppers should not have to go somewhere new. The same agent, with one basket, works in the places they already use:

  • Your app and websiteSDKs for iOS, Android, Flutter, React Native and the web.
  • Your WhatsApp Business numberProduct cards, a basket and a checkout confirmed with a tap.
  • VoiceWhatsApp voice notes, WhatsApp calls and voice calls inside your app, in Arabic and English.
Read moreShow less

Shoppers should not have to go somewhere new. The same agent, with one basket, works in the places they already use:

  • Your app and website. SDKs for iOS, Android, Flutter, React Native and the web. The basket stays in sync with your app's cart. See in-app shopping.
  • Your WhatsApp Business number. Product cards, a basket and a checkout confirmed with a tap. See WhatsApp shopping.
  • Voice. WhatsApp voice notes, WhatsApp calls and voice calls inside your app, in Arabic and English, with a person on hand for any shopper who wants one. See voice ordering.

When is bisky not the right fit?

  • You have no online catalogueThe agent works from your live products, prices and stock.
  • You want to replace site searchbisky does not power your search bar or category pages.
  • You want self-serve sign-upAccess is by invitation, after a demo on your own catalogue.
Read moreShow less
  • You have no online catalogue. The agent works from your live products, prices and stock. Without them it has nothing to shop.
  • You want to replace site search. bisky does not power your search bar or category pages.
  • You want self-serve sign-up. Access is by invitation, after a demo on your own catalogue.

How do you go live? Three steps.

  1. 01

    Connect your catalogue

    Salla, Zid, Shopify, WooCommerce, a product feed or your API, with each branch's prices and stock.
  2. 02

    Set the rules and test

    Persona, languages, products you never sell, handover. Then a test suite built from your own catalogue.
  3. 03

    Go live channel by channel

    In your app first, or WhatsApp first. Add voice orders when you are ready.
FAQ

Ecommerce AI agents, answered.

Want the answer on your own products? Ask us and we will run it.

Write to hello@bisky.ai

What is an ecommerce AI agent?

An ecommerce AI agent is software that shops a store's catalogue for a customer. It reads a request in plain language, searches the live catalogue, checks the results, adds products to the basket and prepares the checkout. A chatbot only answers. An agent acts, within rules the store sets.

What is the difference between an AI agent and a chatbot for ecommerce?

A chatbot answers questions, usually from help-centre content. An ecommerce agent uses tools: it searches the catalogue with real prices and stock, changes the basket and builds a checkout. bisky is an agent, and it still never places an order without the shopper's confirmation.

Can an AI agent place orders on its own?

Not with bisky. It fills the basket and builds the checkout, but the order is placed only after the shopper confirms: a tap, a signed checkout page, or the keypad after the basket is read back on a call. A typed or spoken yes alone never places an order.

Does it replace our site search?

No. Your search bar and category pages keep their search engine. The agent answers requests people make in sentences, such as a budget, a recipe or a list, in your app and on WhatsApp, typed or by voice.

Does it replace our customer service tools?

No. It is built for shopping, not for returns, refunds or delivery complaints. Every conversation is in a shared inbox where a person can take over.

Which platforms does it work with?

Salla, Zid, Shopify, WooCommerce, product feeds, and our REST API with webhooks for retailers with their own platforms. Each branch can keep its own prices and stock.

What is agentic shopping?

Agentic shopping means an AI agent does the work of finding and choosing products and filling the basket, while the shopper approves the result. In grocery that means lists, recipes, budgets and repeat orders handled in a sentence.

How is bisky priced?

Pricing is a proposal per retailer and depends on your stores and the channels you use. Book a demo and we will send one.

Book a demo

Try it on your own catalogue.

Reading helps. Seeing your own products in the answers helps more.