E-commerce AI training: a step-by-step guide

An e-commerce brand’s inbox is always full of the same questions: "When does shipping arrive?", "Will this size fit me?", "How do returns work?", "Is it in stock?", "Where is my order?". Dozens of comments pile up under a single product, dozens of size questions land in DMs, dozens of tracking requests hit email. The team drops its real job (closing a new customer) to churn out copy-paste answers all day. A customer writing from abroad waits for hours. The "I’ll buy right now, is there a discount?" message that arrives at 11 PM waits until morning, and by then the customer has bought elsewhere.

inTusell takes over this load. To do that, it first has to learn your brand, your products, and your sales style. This article explains step by step how an e-commerce brand trains the inTusell AI from scratch. It is the e-commerce chapter of our sector-based "how to train your AI" series, and the main article of that series.

Quick answer

Why does training matter?

inTusell is not a simple chatbot; it is an AI sales assistant and CRM that answers messages on WhatsApp, Instagram and web chat, books appointments and opens orders, and follows each customer through the sales pipeline. It works like an experienced online sales advisor. An experienced salesperson cannot start on day one without knowing your store either. They need to know which products you sell, your shipping and return routine, and which questions to leave to the team. Training makes the AI do two things correctly: give the right information (product details, shipping times, return terms) and give it the right way (your brand voice, tone, and sales discipline).

An untrained assistant either gives overly generic answers or guesses on a topic it doesn’t know. In e-commerce, guessing is costly. A wrong shipping time brings complaints, made-up stock means cancellations and returns, and a wrong price loses the customer. A well-trained assistant stops when it doesn’t know, says so honestly, and connects the customer to the live team: talking in the right places and staying quiet in the right places.

Who is it for?

This guide is for e-commerce teams whose inbox is dominated by product and order questions and who answer the same things over and over:

• Brands selling through their own site, Shopify, WooCommerce, or a marketplace
• Fashion, cosmetics, accessories, and home-goods sellers who get dozens of DMs and comments a day from Instagram and WhatsApp
• Everyone overwhelmed by message volume, from a one-person team to a 10-person support department
• Brands selling abroad that need to communicate in several languages
• Anyone who wants to re-engage customers who stall at checkout or say "let me think" and disappear

You don’t need a technical team. You complete every step below from sections in the panel, without writing code.

The structure of training: 4 core steps + 2 continuous steps

Splitting the training into two groups makes your job easier. The first 4 core steps get the assistant up and running; you do them once. The 2 continuous steps that follow (reviewing and turning fixes into rules, and opening channels) are the ongoing part you keep sharpening as you use the assistant. Here they all are, in order.

1. Upload the knowledge base

The foundation of training is the knowledge base (RAG). In the panel’s Knowledge Base section, you upload all of your brand’s written information. Each time the AI generates a response, it searches these sources and uses only the information written there. This is the technical answer to the "don’t let the AI make things up" worry: the AI talks about whatever you hand it, and nothing else.

Supported source types:

Every file you upload is chunked automatically and made searchable with pgvector. Upload a size-chart CSV, and when a customer asks "Which size for 1.70 m and 65 kg?", the AI finds the right row and responds.

The must-haves for an e-commerce brand: product descriptions and specifications, shipping times and fees, return and exchange terms, size charts, payment methods (cash on delivery, installments), campaign rules, and the most frequently asked questions. Once these are in, most recurring questions get answered automatically. The details are in order and product question automation.

One important note: if your catalog changes often (new products, prices, stock), connecting your store is the most reliable route. Under My business › Channels › Store Integrations you connect a store such as Shopify, WooCommerce, Trendyol, ikas, Hepsiburada or PrestaShop (beta); stock and order status are read from there, the AI says in stock or out of stock but never the count, and the purchase happens on the store’s own checkout. Without a connected store, keeping the knowledge base current is up to you: upload the updated file, and the AI uses the new information in its next response. It knows whatever you give it, and it says when it doesn’t know.

2. Set the persona and tone

You taught the AI what to say in the first step. Now you define how it says it. There are two settings in the panel:

• Assistant name (ai_persona_name): The name it uses to introduce itself to the customer. Most brands use a real advisor’s name from the team, or a name that fits the brand.
• Tone (ai_tone): Whether it speaks warm and friendly, corporate and crisp, or fast and energetic.

A young streetwear brand and a boutique jewelry brand won’t share a tone. The first might speak casually, with humor; the second, elegantly and formally. This setting shapes the AI’s message style on every channel, so the tone in an Instagram DM matches the tone on WhatsApp.

A note on languages: the AI responds in whatever language the customer writes in. When a customer from abroad writes in English or German, you do nothing extra: the assistant detects the language and responds in it while keeping your tone.

3. Define the response rules

The persona defines who the assistant is; the response rules define how it behaves. This is where you pass your sales discipline on to the AI. With the AI Manager Chat, you add rules by writing in plain language, just as you would brief a teammate.

Typical rules for e-commerce brands:

• "If you’re unsure about price, stock, or shipping information, don’t make it up; say you don’t know and hand the conversation off to the team."
• "If the customer is undecided, suggest a size/product, but don’t apply pressure."
• "When asked about returns/exchanges, read the policy from the knowledge base clearly; add no commentary."
• "Share a discount code only for defined campaigns; don’t invent a discount on your own."
• "When a customer complains about a shipping delay, apologize first, give the status, and hand off to the team if a fix is needed."

The most common mistake in e-commerce is an AI guessing just to say something, and that guess turning into a cancellation, a return, or a bad review. In inTusell, the AI is told from the start to "speak only from the sources, never invent price or stock"; it won’t quote a price that isn’t in the knowledge base or the store. This is a working rule, not a guarantee: reliability comes not from a wall that blocks everything but from constraining the AI correctly from the start and from your own checks in the first weeks.

To compare two AI tones, you can use the A/B test, which is in beta: for example, a more formal and a friendlier tone run side by side, each on half of the replies, and the experiment card shows which one leads to more wins. Today only the tone changes; the content and the rules stay the same.

4. Teach from past sales conversations

This is the step that moves training from good to specific to your brand. In the panel, you upload audio recordings of your past sales conversations (MP3, MP4, WAV, M4A) and mark each one Won or Lost: did the customer complete the order, or leave it in the cart?

The system uses these recordings in two ways:

From these, the AI learns how your best salesperson explained value to someone who said "it’s too expensive" and moved a "let me think about it" toward an order. On the KVKK side, uploading requires explicit consent, and phone numbers, emails, ID and card numbers are masked in the transcript before processing.

This step is not mandatory, but don’t skip it. The knowledge base teaches the AI what it knows; past conversations teach it how you sell. Put the two together and the assistant really does resemble an experienced online sales advisor.

5. Review and turn fixes into rules (ongoing step)

The first four steps get the AI working; what comes next sharpens it to your brand. You check replies in AI Test by asking questions as a customer would, and in real conversations under Conversations.

When you see a wrong or missing answer, make the fix permanent. Say the AI described a shipping time incompletely: add the shipping policy to the knowledge base. If it called a product by the wrong name or recommended something without asking the size, write a rule in AI Rules, turn on a ready rule pack in the Behavior Library, or tell the AI Manager Chat in a plain sentence ("ask for the size before recommending"). For a period when you want to see every reply before it goes out, put the account in Full approval or one conversation in Approval mode.

The Label Manager is a separate thing: customer satisfaction replies, the outcome of handed-off conversations, won/lost classification and labels your team adds by hand land there. You approve, reject or edit them; corrections are kept as a quality record, but they do not change how the AI writes replies today. What changes behavior is the knowledge base and the rules. We recommend a short daily look in the first weeks.

6. Open the channels (ongoing step)

Once training is ready, you put the assistant in front of customers. inTusell gathers every channel in a single inbox: WhatsApp, Instagram DM, Instagram comments, Telegram, and web chat. Whichever channel a customer writes from, the same trained assistant responds with the same information.

How you open each channel:

• Instagram: connected through Meta login; you pick your Facebook Page and Instagram account. The account must be a professional account linked to a Facebook Page.
• WhatsApp: under My business › Channels › Messaging Channels you click "Connect with QR" and scan the code on your phone under WhatsApp › Settings › Linked Devices › Link a Device; if you have no second screen, "Link with phone number" gives you an 8-character linking code for your number that you type into the same menu. The number stays the same and no Meta Business approval is required. The official WhatsApp line (Cloud API) opens after Meta approval.

DM replies are already on once Instagram is connected. Comment replies (the "price?", "in stock?" comments under product posts) have their own switch on the Instagram card ("Instagram comments"), and it is on by default; if you like, switch it off and start with DM replies only. If you connected Instagram before September 24, 2026, you need to reconnect it once for comments.

There are three account-wide AI modes. Intern (the default) sends replies itself and asks you before a cancellation or refund. Senior also handles cancellations and refunds itself. In Full approval, every reply on WhatsApp, Instagram and Telegram waits for your approval in Decisions › Approval Queue. Whatever the mode, when the AI is unsure or a sensitive case comes up, it hands the conversation to the team; the handoff lands on the Decisions screen with the full history. One note: a file, image, audio, or video attachment arriving is not on its own a reason to hand off. The AI tries to make sense of the attachment and hands off only when it can’t complete the task.

Once the channels are open, CRM and proactive follow-up kick in: a customer who said "let me think" and disappeared receives up to 3 follow-up messages written by the AI; they go out only within business hours on WhatsApp, Instagram or Telegram and stop when the customer replies, pays or says "don’t write". A separate article covers all the details of daily operations, from incoming message to sale, follow-up, and handoff: how an e-commerce brand uses inTusell.

How long does training take?

How long it takes depends mostly on whether your documents are ready. The steps of a working setup:

1. Uploading the first files to the knowledge base
2. Persona, tone, and first response rules
3. Connecting channels
4. First test conversations

But there is no moment when training is done. Over the first weeks, adding what you notice in AI Test and in real conversations to the knowledge base and the AI rules sharpens the assistant to your brand, and past conversation recordings and A/B tests keep improving it after that. Setup happens once; mastery is continuous.

What it isn’t

Putting inTusell in the right category matters, because the wrong expectation leads to the wrong setup.

• It is not a simple chatbot that gives canned answers. It is not a decision tree; it is an AI sales assistant and CRM that answers messages, opens orders and follows the customer through the sales pipeline, representing your brand as well as you train it.
• It is not a tool that fabricates price or stock. It uses only your knowledge base and your connected store. It says when it is unsure and hands off to the team. This is the most important trust message.
• It is not an e-commerce platform (Shopify/WooCommerce) or a payment system. It does not replace your store. You always close the sale and issue the invoice, and inTusell is not a party to the payment.
• It is not a stock notification service. It does not send a bulk notification when stock arrives. It is an assistant that writes up to 3 follow-up messages to a customer who went quiet.

In short: it is not a bot that spits out an answer to a single question. It is a sales assistant that represents your brand as well as you train it, and never fabricates what it doesn’t know.

Frequently asked questions

How long does e-commerce AI training take?

A working setup comes down to these steps: uploading the knowledge base, setting the persona and tone, writing a few response rules, and connecting channels. How long it takes depends mostly on how ready your documents are; the real refinement comes in the first weeks, as you add what you notice in AI Test and in real conversations to the knowledge base and the AI rules. Training is not a one-time job; it is continuous.

Do I need technical knowledge to train the AI?

No. You do all the training from the panel; no code, API key, or developer is required. You upload PDF, Excel or CSV files to the knowledge base, have your site scanned, choose the persona, and write response rules in plain language. You connect Instagram through Meta login and WhatsApp with a QR code or a linking code for your phone number.

Does the AI give wrong or made-up product/stock/price information?

No. The AI uses only the information in your knowledge base and your connected store; it says in stock or out of stock, never the count. It never invents a price, stock status, or shipping detail it is unsure about; when it does not know, it says so honestly and hands the conversation off to the team. This is the behavior that earns the most trust in e-commerce.

Which channels can I connect?

WhatsApp, Instagram DM, Instagram comments, Telegram, and web chat are gathered in a single inbox. Instagram connects through Meta login; WhatsApp connects with a QR code or with an 8-character linking code for your phone number, with no Meta approval needed. If you connected Instagram before September 24, 2026, you need to reconnect it once for comments.

Can the AI answer order, shipping, and return questions?

Yes. Once you upload shipping times, return and exchange terms, the size chart, and product details to the knowledge base, the AI answers these recurring questions automatically. If your store is connected it also gives order status: if the customer writes on WhatsApp the order is found from that number, on other channels the order number is requested. When it is unsure, it hands off to the team.

Is my data safe under KVKK?

Yes. Data is stored encrypted and each business’s data is kept separate from the others; you can download your account data under Download my data (KVKK), and you manage the KVKK notice your customers receive, with your own privacy-notice link, under Legal notices. Uploading call recordings requires explicit consent; phone numbers, emails, ID and card numbers are masked in the transcript before processing.

Next step

You’ve trained your assistant; next comes using it in daily operations. The next article in the series explains how to run the inTusell you trained on a real workday: incoming product questions, order status, receipt approval, returns, and handing off to the team. Continue straight from there with how an e-commerce brand uses inTusell. For the details of channel setup, the Instagram and WhatsApp sales automation article is ready too.

We wrote this guide for e-commerce, but the same step-by-step logic works in every sector. Take a look at the main articles for neighboring sectors: AI training for real estate, AI training for tour agencies, and AI training for clinics. If you’d like to see a setup tailored to your brand live, use Request a demo and we’ll open your panel together in a short session, or write to hi@intusell.com. The e-commerce solution and solutions pages hold the full set of e-commerce capabilities, the pricing page covers packages and quotas, and the all articles list holds the other guides.