Instagram boutique AI training: a step-by-step guide

An Instagram boutique’s DM inbox is always full of the same questions: "Which size is this?", "I’m 1.65 m, 60 kg: would it fit me?", "Is it in stock?", "Price?", "How many days for shipping?", "Are there color options?". You post a story and soon dozens of "price?" messages land. The post fills up with comments. You go live in the evening and hundreds of messages pile up in the "is it here yet, is it here yet" rush. While you reply to one person, three customers decide "they’re not responding" and buy from another boutique. And the customer who at 11 p.m. says "I want this right now, can you send the IBAN?" is left until morning, by which point the impulse has faded.

inTusell takes over this load. But to do that, it first needs to learn your boutique, your products, and your sales style. This article covers Instagram boutique AI training: how an Instagram boutique or online clothing seller trains inTusell’s AI from scratch, step by step. It is the main article of the Instagram boutique chapter in our sector-based "how to train your AI" series.

Quick answer

Why is training important?

inTusell is not an off-the-shelf chatbot; it’s an AI sales assistant that behaves like an experienced DM sales advisor. No good boutique salesperson starts on day one without knowing your collection: they need to know which products you sell, your size and fit scheme, your shipping and return conditions, and which questions to leave to you. Training teaches the AI to do two things well. First, give the right information: size, price, fabric, shipping. Second, give it in the right way: your brand voice, your tone, your sales discipline.

An untrained assistant either gives very generic answers or guesses on something it doesn’t know. In boutique sales, guessing is expensive. A wrong size recommendation means a return, made-up stock information means an "I placed an order but it was out of stock" complaint, 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 team. That’s why the real aim of training isn’t to make the AI talk a lot; it’s to make it talk correctly and stay silent in the right place.

Who is it for?

This guide is for Instagram boutiques and online clothing sellers whose DM and comment inboxes are dense with size and stock questions, answering the same questions over and over:

• Women’s, men’s and children’s clothing, shoe, bag, jewelry, and accessory boutiques selling only from Instagram or from Instagram + WhatsApp
• Sellers crushed under the DM load of live and story sales, working alone or with a small team
• Brands that can’t keep up with the "price?" questions under comments and the incoming DMs
• Ready-to-wear, second-hand / vintage, designer boutiques, and online clothing stores doing dropshipping
• Those who want to re-engage customers who said "let me think about it," "let me ask my spouse," and disappeared

You don’t need a technical team. All of the steps below are completed from sections in the panel, without writing code.

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

Splitting training into two groups makes the job easier. The first 4 core steps get the assistant working; they are the part of setup you do once. The 2 ongoing steps that follow (reviewing and turning fixes into rules, and opening the channels) are the continuing part where you sharpen the assistant as you use it. You’ll find all of them in order below.

1. Upload the knowledge base

The foundation of training is the knowledge base. In the panel, under My business › Knowledge › Knowledge Base, you upload your boutique’s information. Every time the AI produces a reply, it searches these sources and uses only the information written there. This is the answer to your "don’t let the AI make things up" worry: the AI talks about whatever you hand it.

Supported source types:

Files can be up to 50 MB, and you can upload images too. Every file you upload is automatically split into chunks and made searchable. When you upload a size and measurement chart CSV and a customer asks "which size for 1.65 m, 60 kg?", the AI finds the right row and answers. When you upload a product list, it answers "do you have the brown one, is there any S left?" with the information in that list.

What an Instagram boutique must upload: product names and descriptions, the size and measurement chart (bust-waist-hip, shoe size equivalents), fabric and care information, color and stock status, shipping times and fees, return and exchange conditions, the payment methods you offer, and the most frequently asked questions. Once you upload these topics, the AI answers most of the repeated questions in your DM inbox.

An important note: if your product list changes often (new products, sold-out sizes, price updates), keeping the knowledge base current is in your hands. Once you upload the current file, later replies use the new information. The AI won’t present an "S is available" from an old list as "current"; it knows what you gave it, and it says what it doesn’t know. If your store (Shopify, ikas, Trendyol and others; integrations are in beta) is connected, stock comes from there: the AI says in stock or not, never how many are left.

2. Set the persona and tone

In the first step you taught the AI what to say; now you’ll determine how it’ll say it. There are two settings in the panel:

• Assistant name: The name it’ll introduce itself to the customer with. Most boutiques use a real advisor’s name from the team or a warm name that fits the brand.
• Tone: Whether it’ll speak in a friendly and casual way, an elegant and calm way, or a fast and energetic way.

A young streetwear boutique and an elegant evening-gown boutique won’t have the same tone. The first can speak in a relaxed, witty, informal voice; the second in a polite, elegant, formal voice. Given the nature of Instagram, most boutiques prefer a friendly, informal voice, but this setting depends entirely on your brand personality. The tone you set carries into the AI’s voice on every channel: the tone in Instagram DM stays consistent with the tone on WhatsApp.

Multilingual note: the AI replies 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 replies in it while keeping your tone. Fixed system messages such as reminders go in Turkish to Turkish speakers and in English to everyone else.

3. Define the response rules

The persona defines "who it is," and the response rules define "how it’ll behave." This is where you transfer your sales discipline to the AI. You write them in AI Rules, turn on ready rule packs in the Behavior Library, or add rules in AI Manager Chat by writing in plain language, just like instructing a teammate.

Typical rules for Instagram boutiques:

• "If you’re not sure about size, stock, or price information, don’t make it up; say you don’t know and hand the chat to the team."
• "If the customer gives measurements, suggest the suitable size from the size chart, but don’t say 'it’ll definitely fit'; say 'these measurements usually fit size X.'"
• "When returns or exchanges come up, read the policy clearly from the knowledge base, don’t add commentary."
• "Once an order is finalized, communicate the shipping time clearly."
• "If the customer says 'I’ll think about it,' don’t pressure them; remind them of the product’s standout feature and leave it warm."

If you sell by bank transfer, you don’t need a separate rule for the IBAN: the order lands in the receivables ledger (Tahsilat defteri), the AI sends the amount, IBAN and reference code in one fixed message, your team approves the receipt, and the AI never says "your payment was received" before that approval.

The most common mistake in boutique sales is an AI throwing out a size or stock figure it doesn’t know "just to say something," and that turning into a return or an "I placed an order but it was out of stock" complaint. In inTusell the AI is told from the start to "speak only from the sources, never invent size, stock or price"; it won’t state 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 the AI being correctly constrained from the start and from your 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 it from past sales conversations

This is the step that takes training from "good" to "specific to your boutique." In the panel, you upload audio recordings of your past sales conversations (MP3, MP4, WAV, M4A) and mark each one as Won or Lost: for example, did the customer complete the order, or say "let me think about it" and leave?

The system uses these recordings in two ways:

This way, the AI learns from won conversations how your best salesperson explains fabric and fit quality to someone who says "it feels a bit pricey," and how they keep someone who says "let me ask my spouse" warm and move them to an order. Uploading recordings requires explicit consent; phone numbers, emails, ID and card numbers are masked in the transcript before processing.

This step isn’t mandatory, but don’t skip it. The knowledge base teaches the AI "what" it knows; past conversations teach it "how you sell." When the two combine, the assistant truly resembles an experienced DM 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 boutique. 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 size incompletely: update the size chart in the knowledge base. If it called a product by the wrong name or recommended a size without asking for measurements, 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 measurements before recommending a size"). Over time, patterns specific to your boutique (your product names, your campaign lines, your brand voice like "I styled it," your way of handling returns) build up in the knowledge base and the rules. 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: connects through Meta login: you pick your Facebook Page and Instagram account, with no keys or tokens to copy. 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.

For an Instagram boutique, the right starting point is WhatsApp and Instagram DM. Most sales already flow into DMs with a "DM us" call, and the assistant handles that traffic after hours too. We don’t promise seconds on Instagram: for most business accounts Instagram messages are fetched at intervals, which can take a few minutes. 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; the AI writes one public reply to each comment. 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 special request comes up, it hands the conversation to the team; the handoff lands on the Decisions screen with the full history. One note: a product photo, screenshot, or voice message a customer sends is not on its own a reason to hand off; the AI tries to make sense of the attachment (for example, it tries to interpret an image sent with "do you have this model?") 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". This is the most neglected part of boutique sales. A separate article covers all the details of daily operations, from an incoming DM to a sale, follow-up, and handoff: how an Instagram boutique 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 product list, size chart, and first files to the knowledge base (shorter if your Excel list is ready)
2. Persona, tone, and the first response rules
3. Connecting WhatsApp and Instagram DM
4. The first test conversations

But there’s no "training is done" moment. As you add the gaps you spot in AI Test and in real conversations to the knowledge base and AI rules in the first weeks, the assistant sharpens to your boutique; past call recordings and A/B tests are ongoing improvements too. Setup is done once; mastery is continuous.

What it isn’t

Putting inTusell in the right category matters, because wrong expectations lead to the wrong setup.

• It is not a chatbot that gives canned answers. 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 tool that invents size, stock or price. It only uses the information you upload; it says when it’s not sure and hands off to the team. This is the most important trust message.
• It is not an e-commerce infrastructure or payment system. It doesn’t replace your store or your checkout; payment happens on your store’s checkout or by bank transfer, and your team approves the receipt. inTusell isn’t a party to payment.
• It is not a "notify me when back in stock" service. It’s not a system that announces a sold-out size to everyone at once; it’s an assistant that sends a quiet customer follow-up messages written for that conversation.

In short: not a bot that spits out an answer to a single question, but a sales assistant that represents your boutique to the extent you train it and doesn’t make up what it doesn’t know.

Frequently asked questions

How long does Instagram boutique AI training take?

A working setup consists of these steps: uploading product, size and shipping information to the knowledge base, setting the persona and tone, a few response rules, and connecting WhatsApp and Instagram DM. How long it takes depends mostly on how ready your documents are; the real refinement builds up as you add the gaps you spot in AI Test and in real conversations to the knowledge base and AI rules in the first weeks. Training isn’t one-time; it’s continuous.

Do I need technical knowledge for AI training?

No. All training is done from the panel; no code, API key, or developer is needed. You upload your product list (Excel or CSV), your size chart, and frequently asked questions to the knowledge base, pick the persona, and write the response rules in plain language. You connect Instagram through Meta login (picking your Facebook Page and Instagram account) and link WhatsApp with a QR code or an 8-character linking code.

Will the AI give wrong or made-up size/stock/price information?

The AI uses only the information you upload to the knowledge base and the data in your connected store; it doesn’t invent a size, stock status, or price it’s unsure of. When it doesn’t know, it says so honestly and hands the chat to the team. With a connected store it says in stock or not, never how many are left.

Does it also automatically answer "price?" questions in Instagram comments?

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

Can the AI answer size, stock, and shipping questions and move them to an order?

Yes. When you upload the size chart, shipping times, product details, and payment methods to the knowledge base, the AI answers these repeated questions; with Payment tracking on, once it confirms the product and amount with the customer, it opens the order and sends an order tracking link. With a connected store, payment happens on your store’s own checkout. When it’s unsure, it doesn’t add commentary; it hands off to the team.

Is my data safe under KVKK?

Data is stored encrypted and each business’s data is kept separate. You export your data with "Download my data (KVKK)" under My business › Business Info; "Legal notices" in the same place sends your customers a KVKK notice with your own privacy link. 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 is using it in day-to-day operations. The next article in the series explains how to run the inTusell you trained on a real workday: an incoming size question, the "price?" downpour, cart and DM recovery, shipment tracking, and handoff to the team. Continue straight from there: how an Instagram boutique uses inTusell. For the details of channel setup, the Instagram and WhatsApp sales automation article is ready, and for the finer points of selling from DMs, the selling from DMs automation article.

This guide was written for Instagram boutiques, but the same step-by-step logic works in every sector. You can also take a look at the main articles of neighboring sectors: AI training for e-commerce, AI training for dental clinics, AI training for travel agencies, and AI training for clinics. If you’d like to see the setup specific to your boutique live, let’s open your panel together in a short session with Get a demo, or write to hi@intusell.com. You can find all of the Instagram boutique capabilities on the Instagram boutiques solution and solutions pages, the package and quota details on the pricing page, and for other guides, take a look at the all articles list.