Instagram boutique inTusell usage: a daily operations guide

In the main article you trained inTusell’s AI: you uploaded your product catalog, your size chart, and frequently asked questions to the knowledge base, marked your won sales conversations, and set the persona and response rules. Training was a one-time setup. Now the real work begins: how does Instagram boutique inTusell usage work in day-to-day operations? This article shows, step by step, what the assistant you trained actually does over a workday in the field, from an incoming DM to an order, from follow-up to handoff to a human.

This article is the second part of the Instagram boutique chapter of our sector-based "how to train your AI" series. The first part, how to train inTusell’s AI, explained the setup; this article explains turning that setup into day-to-day operations.

Quick answer

The flow of a day

A day for a boutique team that has set up inTusell looks very different from before. A one-person boutique used to wake up in the morning and work one by one through dozens of "do you have this, how much?" DMs piled up overnight, and some of those customers had already bought from another boutique. Now the messages that arrived at night are answered, and what the team needs to look at is lined up in Decisions. The backbone of a day works like this:

The team no longer spends the day scanning DMs. It deals with the conversations that truly need a decision, and with making content.

Who is it for?

This usage model makes the most sense for these Instagram boutiques and online clothing sellers:

• Boutiques that receive heavy size and stock questions from DMs: those who can’t keep up with the "do you have this, how much?" downpour after every post.
• Sellers who lose requests outside business hours: those who lose the customer to a competitor because evening and weekend questions are answered late.
• Boutiques with a high volume of repeated questions: brands where size, measurement, shipping, return, and payment questions come in the same patterns.
• Boutiques managing multiple channels with one person or a small team: those who have to follow DMs, WhatsApp, and comments at the same time.

If you have a DM volume you can’t keep up with on your own, inTusell works like an experienced salesperson handling that demand: it answers the questions and moves them toward an order while you produce content.

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

The flow starts when the customer sends a DM. Imagine someone writing from Instagram DM, "is the brown knit from the Story still available, I’m a size 38." The AI reads this message, scans the product descriptions and the size chart in your knowledge base, suggests the product that matches the customer’s need, and routes to the order.

Important point: the AI replies in whatever language the customer writes in. For boutiques selling abroad, this is critical: a size question that comes in English gets an English reply, with no extra setting.

A common situation at a boutique is the customer asking "which size should I get?". If you added the rule "clarify the measurement before giving a recommendation" in AI Rules, the AI first asks for height, weight or the measurement, then routes from the size chart. That way the recommendation isn’t random; it’s based on the customer’s actual measurements: the simplest way to prevent wrong-size returns. We explain separately how all of these channels come together in a single inbox in the Instagram and WhatsApp automation article.

Selling from DMs: size, stock, and price questions from the knowledge base

At a boutique, most incoming messages are not new sales but repeated product questions: "What sizes does this come up to?", "How many days for shipping?", "How do returns work?", "Bank transfer or card?" These questions come in the same pattern throughout the day. inTusell takes this load by answering from the knowledge base.

The most critical rule here is this: the AI does not invent price and stock. It answers only from the sources you uploaded to your knowledge base or from your connected store:

At a boutique, stock changes fast: after a post, a size can sell out within hours. Without a connected store, the AI answers the general size range and measurements from the knowledge base and leaves an exact "do you have it in hand right now?" check to the team. If asked for information that isn’t in the knowledge base, the AI says it doesn’t know instead of inventing it and hands the chat to the team. This keeps you from having to tell a customer "yes, we have it" and then "sorry, it’s gone"; that is the foundation of trust.

You’ll find this engine (answering product, size, and stock questions from DMs with the knowledge base) in detail in the DM sales automation article.

Orders, payment and "where’s my order?"

With Payment tracking on, once the customer confirms the product, size and amount, the AI opens the order and sends the customer an order tracking link. If your store (Shopify, ikas, Trendyol and others; integrations are in beta) is connected, the purchase and payment happen on your store’s own checkout; the AI makes no separate payment link.

If you sell by bank transfer, the order lands in the receivables ledger (Tahsilat defteri): the AI sends the amount, IBAN and reference code in one message. When the customer sends a receipt, it goes to your team for approval; the AI never says "your payment was received" before that approval. Payment reminders are off by default; you can turn them on.

When a customer asks "where’s my order?" on WhatsApp, the order is found from the number they are writing from; on Instagram, web chat or from a different number the AI asks for the order number. A phone number typed into the chat does not open someone else’s order. A conversation counts as won once an order or payment record exists; the AI’s own guess never marks a sale as won.

How the knowledge base is fed and kept current

The AI answering correctly depends on how current your knowledge base is. My business › Knowledge › Knowledge Base is fed from these sources:

• Files: The product catalog, size chart, and shipping and return policy are uploaded as PDF, Word, Excel, CSV, TXT or image files (up to 50 MB); product name, description, size and color options, and price come from here.
• Website scan: You give your site’s address; the content is scanned and re-scanned every week.
• Instagram profile: You import the last 100 posts from your profile; the product information in post captions goes into the knowledge base.
• FAQ suggestions: Suggestions drawn from customers’ most frequent questions are added once you approve them.

For a short-lived note like "free shipping this week", re-upload your current shipping file or tell the AI in a plain sentence in AI Manager Chat. Stock and price change often at a boutique; when you update your catalog, you refresh the knowledge base too. The AI always speaks according to the latest source you uploaded: if the source isn’t current, the AI isn’t either. Updating the catalog when you drop a new collection is the backbone of the operation.

Winning back the quiet customer: proactive follow-up and CRM

At a boutique, most sales melt away with customers who say "let me think about it" or "I’ll get back to you tonight" and disappear. inTusell doesn’t forget these customers. A customer who got information and went quiet receives up to 3 follow-up messages written by the AI itself; 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. Follow-up stops when the customer replies, pays for an order or says "don’t write to me".

A follow-up message is not a canned template; it is written for that conversation, in a tone like "Writing about the knit you asked about; is size 38 still of interest?". Every conversation is logged in the CRM; the customer’s history, which product they asked about, and the stage they’re at stay on record. When you sit down to operations in the morning, it’s clear which customer is warm and which is waiting for a follow-up; you don’t need to keep a reminder list by hand.

Appointment flow (if needed)

Most boutique flows run through orders, but some boutiques use appointments too: a showroom visit, coming in for a fitting, or a custom-tailoring consultation. inTusell’s appointment engine works in these cases too.

The AI doesn’t pull a time out of thin air. 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 your working hours 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 can’t take the same time. Reminders go out 1 day and 2 hours before; the 1-day message asks "1 Yes · 2 Reschedule · 3 Cancel" and carries a change or cancel link. Reminders run on paid plans. Appointments are copied one way to Google Calendar (inTusell → Calendar); an event you add in Google by hand does not block the slot in inTusell. This module can be turned on in every plan; if you don’t need it, you never use it.

Handoff to a human: operating modes

You decide how independently the AI works. There are three account-wide modes (My business › Instructions › AI Settings › Advanced AI Settings):

In every mode, the AI hands a stock check it can’t answer or a request outside the knowledge base to the team. The handoff lands on the Decisions screen with the full chat history; the customer doesn’t have to start over. You can put a single conversation, such as a sensitive return dispute, in Approval, Shadow or Paused mode; when you reply by hand from the panel, the AI pauses in that conversation. The details are in Decisions and human approval.

One extra note: when a customer sends a file such as a product photo ("do you have one just like this?") or a shipping label, that alone is not a reason for handoff to a human. The AI takes the attachment, understands the context, and keeps the flow going; a payment receipt goes to your team for approval.

Reports: what’s working, what to fix?

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

1. Finding gaps in the knowledge base: If there’s a topic where the AI keeps saying it doesn’t know and handing off, that information is missing from the knowledge base; once you add it, the AI answers that question itself. For example, if "do you offer cash on delivery?" keeps getting handed off, you need to update the payment note.
2. Improving response rules: When you see a wrong or missing answer, you write a rule in AI Rules, turn on a ready rule pack in the Behavior Library, or give a plain-language instruction in AI Manager Chat ("ask the size before quoting a price"). Approvals and corrections in the Label Manager are kept as a quality record; they do not change the AI’s replies on their own. The A/B test (beta) compares tone only: replies are split 50/50 between, say, a formal and a friendly tone.

So the reports aren’t just a summary; they’re the feedback loop for sharpening the assistant over time.

What it isn’t

To put inTusell in the right category, let’s be clear about what it isn’t:

• 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.
• Not an e-commerce platform or payment provider. It doesn’t replace your boutique; payment happens on your store’s checkout or by bank transfer, and your team approves the receipt. The seller is the boutique.
• Not a source of stock and price. It doesn’t invent information; it speaks only from the source you provide or your connected store, says when it doesn’t know, and hands off.
• Not a bot that replies to every comment. The AI writes one public reply to an Instagram comment, but it does not reply to spam comments that carry links; and if you connected Instagram before September 24, 2026, no comment gets an AI reply until you reconnect once.
• Not a product priced specifically for boutiques. Plans differ only by messages, voice minutes and storage, not by sector; channels are never charged.

So you don’t start with the wrong expectations, let these limits be clear from the outset. For product and pricing details, see the Instagram boutiques solution and pricing pages.

Frequently asked questions

Does the AI complete the order on its own?

The AI suggests the product, answers size, color and stock questions from the knowledge base, and confirms the product and amount with the customer. Without a connected store, and with Payment tracking on, it opens the order after confirmation and sends the customer an order tracking link; for bank transfer it sends the amount, IBAN and reference code in one message, and your team approves the receipt. With a connected store the purchase and payment happen on your store’s own checkout. For situations outside the knowledge base it hands the chat to the team.

Does the AI make up stock and price?

No. The AI states price and stock only from your knowledge base or your connected store; with a connected store it says in stock or not, never how many are left. It does not invent a size, color or stock detail it doesn’t know; it says so and hands off to the team.

How does it answer size and measurement questions?

The size chart, measurement ranges and "which size should I get?" answers are uploaded to your knowledge base; the AI answers these repeated questions from that source. Without a connected store, when an exact stock check is needed, such as "do you have L right now?", it hands the chat to the team.

Does it also auto-reply to Instagram comments?

Yes. The AI writes one short, public reply to each comment and does not reply to spam comments that carry links. Comment replies are switched on or off with the "Instagram comments" switch on the Instagram card, and it is on by default. If you connected Instagram before September 24, 2026, reconnect once. Replying to a comment by private message (Reply with DM) opens after Meta approval.

What happens to a DM that comes in at night?

The AI replies 24/7. A "do you have this dress in M?" question that arrives at 02:00 gets an answer from the knowledge base; if suitable, the AI routes the customer to the product and the order. On most accounts Instagram messages are fetched at intervals, so a reply can take a few minutes. When you open up in the morning, answered questions and handed-off conversations are waiting for you.

Which channels does it bring together in a single inbox?

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

Next step

If you haven’t trained your assistant yet, start with the how to train inTusell’s AI article: the foundation of this operation is built there. To go deeper on the channel side, move to the Instagram and WhatsApp automation article; to detail the flow of selling from DMs, the DM sales automation article; and you can see the Instagram boutiques solution page and the whole series on the all articles page.

To see how it would work live at your own boutique, Get 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.