Using inTusell in e-commerce: a daily operations guide

In the first article, you trained the inTusell AI: you uploaded your product catalog and FAQs to the knowledge base, marked your sales conversations, and configured the persona and response rules. Training was a one-time setup. Now the real work begins: how does an e-commerce business use inTusell, that is, how does using inTusell in e-commerce work day to day? This article walks step by step through what the assistant you trained does over a full workday: from the incoming DM to the order, and from order status to receipt approval and handing off to a human.

This article is the second part of the e-commerce section of our sector-by-sector "how to train your AI" series. The first part, how to train the inTusell AI, covered the setup. This one covers turning that setup into daily operations.

Quick answer

A day in the flow

The typical day of an e-commerce team that has set up inTusell looks very different from before. The customer rep used to come in each morning and work through dozens of unread DMs and unanswered comments one by one. Now the messages that came in overnight are already answered, customers have moved to the right stage of the sales pipeline, and the ones that need a person are queued on Decisions. The backbone of a day works like this:

The team no longer spends its time scanning messages. It spends it on conversations that genuinely need a decision.

Who is it for?

This usage model especially makes sense for e-commerce businesses that:

• Receive heavy product questions via Instagram and WhatsApp: stores that can’t keep up with dozens of "do you have this, how much is it?" messages a day.
• Lose after-hours demand: operations that miss sales because they respond late to questions coming in the evening and on weekends.
• Have a high volume of recurring questions: brands where size, color, shipping, and return questions arrive in the same pattern.
• Manage many channels with a small team: firms forced to track DMs, WhatsApp, comments and web chat separately.

When demand outgrows what a single rep can handle, inTusell meets it like an experienced salesperson.

Incoming request: the customer asks about a product, the AI recommends a suitable one

The flow starts when the customer sends a message. Imagine someone writes via Instagram DM: "I’m looking for navy sneakers, size 42." The AI reads the message, scans the product descriptions in your knowledge base and the products in your connected store, recommends a product that fits the customer’s need, and directs them to the product page.

One important point: the AI responds in whatever language the customer writes in. For brands selling abroad this is critical: a product question that comes in English gets an English reply, with no extra configuration.

If you added the "clarify the need before recommending" response rule during training, the AI first asks about size, color, and intended use. That rule keeps the recommendation from being random; it rests on the customer’s real need. The Instagram and WhatsApp automation article explains separately how all these channels come together in a single inbox.

Order, shipping, and return questions: answered from the knowledge base

In e-commerce, most incoming messages aren’t new sales but recurring operational questions: "How many days does shipping take?", "How do I make a return?", "Is there an exchange on this product?" They cycle in the same pattern all day and eat up the rep’s time. inTusell takes on this load by answering from the knowledge base.

The most important rule here: the AI does not invent price or stock. It answers only from your knowledge base and your connected store:

Store integrations (My business › Channels › Store Integrations; Shopify, Trendyol, ikas, Hepsiburada, PrestaShop and others) are in beta; after connecting, ask about a few products in AI Test to check. If someone asks about information that is in neither the knowledge base nor the store, such as the stock of a size you didn’t upload, the AI does not invent an answer: it says it doesn’t know and hands the conversation to the team. That keeps you from giving the customer wrong stock or price information and then having to correct it; it is the foundation of trust.

The order and product questions automation article gives a detailed account of this engine, from orders and shipping to returns and product questions.

Payment, receipts and order notifications

How the customer is sent to payment is set by "Customer Redirect Mode" under My business › Instructions › AI Settings › "Advanced AI Settings": "Website / Payment Link" or "IBAN / Bank Transfer".

• If your store is connected: the purchase and payment happen on the store’s own checkout; the AI creates no separate payment link.
• If no store is connected: with Payment tracking on, the AI confirms the product and amount with the customer, opens the order and sends the customer an order tracking link.
• Bank transfer: the AI shares your IBAN. If you turned on payment tracking (My business › Channels › Calendar & Payment), each record gets a reference code and the AI sends the amount, IBAN and reference in one fixed message. The receipt the customer sends waits for approval on Decisions; you or your team approve the payment, and the AI never says "your payment has been received" before that. Details in bank transfer receipt and receivables tracking.

As an order moves forward in the connected store, the customer can get a WhatsApp notification. You choose the stages in Store Integrations (Payment received, Preparing, Shipped, Delivered, Cancelled); these messages are fixed templates, not written by the AI. Cash on delivery is not a separate setting: if your store offers it and it shows up in recent orders, the AI mentions it as an option; today this works only for PrestaShop stores.

How the knowledge base is fed and stays up to date

Whether the AI answers correctly depends largely on how current your knowledge base is. You feed it under My business › Knowledge › Knowledge Base from these sources:

• Files: product catalog, size charts and policy texts as PDF, Word, Excel, CSV, TXT or images (up to 50 MB per file). You can add short-lived notes, such as a campaign, as a small file too.
• Website scan: you give your site address; the returns page, shipping FAQ and product pages are read, and the site is re-scanned every week.
• Instagram profile: your last 100 posts are imported; product information in the captions becomes part of the AI’s sources.
• FAQ suggestions: suggestions drawn from customers’ most frequent questions come to you; the ones you approve are added to the knowledge base.

Stock and price change often. If your store is connected, stock status comes from the store; if not, refresh the file in the knowledge base whenever you update your catalog. The AI always speaks from the latest source it has: if the source isn’t current, neither is the AI, which is why a current catalog is the backbone of operations.

The quiet customer: proactive follow-up and CRM

In e-commerce, most sales dissolve among customers who ask about a product, say "let me think about it," and disappear. inTusell doesn’t forget them. A customer who got information and went quiet receives up to 3 follow-up messages written by the AI; wait times are set by sector, and messages go out only within business hours (otherwise 09:00-21:00 local time) on WhatsApp, Instagram or Telegram. The follow-up stops when the customer replies, pays for the order or says "don’t write". Every conversation is logged in the CRM, so the customer’s history, the product they were interested in, and the stage they reached all stay on record.

When you sit down to operations in the morning, you can see which customer is warm and which is waiting for follow-up. Nobody has to keep a manual reminder list.

Appointment and reservation flow (if needed)

Most e-commerce flows revolve around orders, but some businesses also use appointments: a showroom visit, a product consultation call, an installation or assembly appointment, or a trial session. inTusell’s appointment engine works in these cases too.

The AI doesn’t offer times off the top of its head. It first collects the date, time and any note. What happens next depends on your account: if the AI booking tools are on, it checks the working hours you defined and booked times and books the free slot itself; if not, it passes the request to your team with those details, and you confirm the time or the customer picks a free slot on your online booking page. To see which applies, ask for an appointment in AI Test. Either way, two appointments cannot be booked for the same time. A reminder goes out 1 day and 2 hours before each appointment; the 1-day message asks "1 Yes · 2 Reschedule · 3 Cancel" and carries a change/cancel link. Appointments are copied one-way to Google Calendar (inTusell → Calendar); the team sees them in their own calendar, but an event added in Google does not block the slot in inTusell. You can enable this module on any plan; on the Free plan reminders are off.

Handing off to a human: working modes

You decide how much the AI does on its own. There are three account-wide modes (My business › Instructions › AI Settings › "Advanced AI Settings"):

In every mode the AI hands a shipping detail it doesn’t know, or a request outside the knowledge base, to the team; legal and sensitive topics go to the team in every mode too. The handoff lands on the Decisions screen with the full conversation history, so the customer doesn’t have to start over. In a sensitive complaint, switch just that conversation to Approval, Shadow or Paused. You can change the account mode at any time.

One more note: a customer sending a file (a product photo, an invoice, a shipping label) is not on its own a reason to hand off to a human. The AI receives the attachment, understands the context and continues the flow; it hands off only when the situation genuinely needs a decision. A payment receipt is different: it needs payment approval, so it lands on Decisions.

Reports: what’s working, what to fix?

To keep operations visible, you track basic metrics in the panel: how many messages came from which channel, how many the AI answered, how many were handed off to a human, and how many people sit at which stage of the sales pipeline. Seeing these serves two purposes:

1. Finding knowledge-base gaps: if the AI often says "I don’t know" about a topic and hands it off, that information is missing from the knowledge base; add it and the AI answers that question itself.
2. Turning behavior into rules: when you see a wrong or missing answer, write a rule in AI Rules, turn on a ready rule pack in the Behavior Library, or say it in a plain sentence in the AI Manager Chat ("ask for the size before recommending"). Approvals and corrections in the Label Manager are kept as a quality record; they do not change the AI’s replies on their own. To try out tone, the A/B test (beta) compares two tones, such as formal and friendly, by splitting replies half and half.

Reports, then, aren’t just a summary; they are a feedback loop in which you sharpen the assistant yourself.

What it isn’t

To place inTusell in the right category, let’s clarify what it isn’t:

• It’s not a simple chatbot. inTusell 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 is not a flow bot answering from preset templates; it works with the knowledge and sales techniques you trained into it.
• It’s not an e-commerce platform or a payment provider. It doesn’t replace your store; it directs customers to your catalog and your checkout page, and the business remains the seller.
• It’s not a stock and price source. It invents nothing; it speaks only from the sources you provide and your connected store, says when it doesn’t know, and hands off.
• It’s not an e-commerce-specific priced product. Plans differ only by messages, voice minutes and storage, not by sector; channel count is never charged. You can enable the modules on any plan.

Knowing these boundaries from the outset keeps you from starting with the wrong expectation. For product and pricing details, see the solutions and pricing pages.

Frequently asked questions

Does the AI complete an order on its own?

If your store is connected, the AI recommends the product, says whether it is in stock and sends the customer to the store’s own checkout; the purchase and payment happen there, and the AI creates no separate payment link. Without a connected store, and with Payment tracking on, the AI confirms the product and amount with the customer, opens the order and sends an order tracking link; for bank transfer it shares your IBAN. Your team approves the receipt.

Does the AI invent stock and prices?

No. The AI gives price and stock status only from your knowledge base and your connected store; it says in stock or out of stock, never the quantity. It never invents a size, color, or stock detail it doesn’t know; it says it doesn’t know and hands off to the team. This is the most important trust rule.

How does it answer shipping and return questions?

You upload shipping times, return conditions, and the exchange policy to your knowledge base, and the AI answers these recurring questions straight from that source. If your store is connected and the customer writes on WhatsApp, the order is found from that number; on another channel or a different number, the AI asks for the order number and the phone on the order, and gives the status once they match. When it needs a shipping detail it doesn’t have, it hands the conversation off to the team.

Can a customer be connected to a human?

Yes. When the AI is unsure or a conversation needs a person, it hands off to your team; the handoff lands on the Decisions page with the full conversation history. You can take over any conversation at any time, or switch just that conversation to Approval, Shadow or Paused.

What happens to a message that comes in at night?

The AI responds 24/7. A "do you have this size?" question that arrives at 02:00 gets an answer from the knowledge base and the connected store; where it fits, the customer is directed to the product. Follow-up messages do not go out at night; they wait for business hours. When you open up in the morning, answered questions are in the inbox and handed-off conversations are waiting on Decisions.

Which channels does it bring into a single inbox?

WhatsApp, Instagram DM, Instagram comments, Telegram and web chat come together in a single inbox. If you connected Instagram before September 24, 2026, you need to reconnect it once for comments.

Next step

If you haven’t trained your assistant yet, start with the how to train the inTusell AI article: that is where the foundation of this operation gets built. To go deeper on the channel side, move on to Instagram and WhatsApp automation, and for order and product questions, read order and product questions automation. The setup steps are in the e-commerce user guide, the full solution on the e-commerce solution page, and the whole series on the all articles page.

To see live how this would work at your own store, request a demo or write directly to hi@intusell.com. In a short session we open your inbox together and test the first reply in the system.