How does an Instagram boutique use inTusell? A day-to-day operations guide

In the first 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 an Instagram boutique use inTusell — that is, 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 already answered, leads are categorized, and some quiet customers have been re-engaged. 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/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 a senior salesperson handling that demand — it runs the sale 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 product/payment step.

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 response rule "clarify the measurement before giving a recommendation" during training, 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 — one of the simplest ways to lower the return rate. 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 gives the answer only from the source you uploaded to your knowledge base:

Stock is dynamic at a boutique — after a post, a size can sell out within hours. That's why the AI answers the general size range and measurements from the knowledge base but leaves clear stock confirmation — "do I have it on hand right now?" — to the team. If someone asks about something that isn't in the knowledge base, the AI doesn't invent information; it says it doesn't know and offers to connect the customer to the live team. That keeps you from telling a customer "it's available" and then having to say "sorry, it's gone." This is the foundation of trust.

You'll find this engine — automatically answering product/size/stock questions coming from DMs with the knowledge base — in detail in the DM sales automation article.

How the knowledge base is fed and kept current

The AI giving correct answers depends entirely on how current your knowledge base is. inTusell feeds the knowledge base from several sources and indexes all of them for pgvector-based search (RAG):

• Product catalog: Uploaded as PDF, Excel, or CSV; product name, description, size/color options, and price come from here.
• Web URL: You give the address of your website or product pages; the content is pulled and indexed.
• Free text: You write notes like "size chart," "free shipping this week," "5% bank-transfer discount" directly into the panel.

Stock and price change often at a boutique, so refresh the knowledge base whenever you update your catalog. The AI always speaks from the most recent 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 operations.

Recovering the quiet customer: proactive follow-up and CRM

At a boutique, most sales are lost to customers who said "let me think about it" or "I'll come back in the evening" and then disappeared. inTusell doesn't forget these leads. It sends a proactive follow-up message to customers who took information or went quiet at the decision stage, which keeps the lead alive. Every conversation is written into the CRM, so the customer's history, the product they asked about, and the stage they stopped at all stay on record.

One boundary needs stating clearly here: inTusell does not keep a managed "waitlist." What it does is make an opportunistic re-offer to suitable WhatsApp customers being followed up — for example, a reminder along the lines of "the knit you asked about is still ready, would you like it?". So when you sit down to work in the morning, it's already clear which lead is warm and which is waiting for follow-up. You don't have to keep a reminder list by hand.

Appointment flow (if needed)

Most boutique flows run on orders, but some boutiques use appointments too: a showroom/office visit, coming for a fitting, custom-tailoring consultation, or a reservation before a live broadcast. inTusell's universal appointment engine works in these situations as well.

The AI doesn't give out a time off the top of its head; it looks at the working hours you defined during training and the booked slots, and if it finds a suitable slot it creates the appointment. An automatic reminder (for example, 1 day and 2 hours beforehand) goes out for every appointment, and the customer manages their appointment themselves via the /manage-appointment/{token} link — cancellation or rescheduling is done with one click. Appointments are copied one-way to Google Calendar (inTusell → Calendar); the team sees them in their own calendar. This module can be enabled on every plan; if you don't need it, you simply don't use it.

Handoff to a human: lock modes

You determine how autonomously the AI works. There are three lock modes:

In hybrid mode, the AI hands off to the live team any stock confirmation it can't answer — "do you have L right now?" — or a request outside the knowledge base. At the moment of handoff, the team can see the entire conversation history, so the customer doesn't have to start over. You can change the mode at any moment — for example, ai_only during the DM explosion after a live broadcast, human_only during a sensitive return dispute.

An additional note: when the customer sends a file like a product photo ("do you have the same as this?"), a receipt, or a shipping label, this is not on its own a reason for handoff to a human. The AI takes the attachment, understands the context, and continues the flow; it hands off only if there's truly a situation that requires a decision.

Reports: what's working, what should be fixed?

For operations to be visible, you track basic metrics in the panel. How many messages came from which channel, how many were answered by the AI, how many were handed off to a human, which questions repeat the most — seeing these serves two purposes:

1. Finding knowledge-base gaps: If there's a topic the AI frequently says "I don't know" about and hands off, that information is missing from the knowledge base. Adding it lowers the handoff rate. For example, if "is there cash on delivery?" is constantly handed off, the payment note needs updating.
2. Improving the response rules: You review the labels and correct miscategorized conversations; the AI learns from these corrections. If you like, you compare two different response approaches with an A/B test — for example, which converts to more sales, "ask for the measurement first" or "suggest the product first."

So reports aren't just a summary but 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:

• It is not a chatbot. Not a flow bot that answers according to canned patterns; it's a fully autonomous AI sales assistant that works with the information and sales techniques you trained.
• It is not an e-commerce infrastructure / payment provider. It doesn't replace your boutique; it routes to your catalog and your payment method (bank transfer, cash on delivery, card link), and the seller is the boutique.
• It is not a stock and price source. It doesn't invent information; it speaks only from the source you gave, says when it doesn't know, and hands off.
• It is not a guaranteed automation that moves comments to DMs. Instagram comment automation rolls out gradually, subject to Meta approval; the first step that's live is WhatsApp and Instagram DM.
• It is not priced specifically for boutiques. The pricing model is based on message and voice-minute volume and doesn't change by sector. Modules can be enabled on every plan.

Let these boundaries be clear from the start, so you don't begin with the wrong expectation. For product and pricing details, you can look at 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 the size/color/stock question from the knowledge base, and takes the customer all the way to the payment step. At most boutiques, payment is completed with bank transfer/EFT, cash on delivery, or a card link; the AI states the right option from the knowledge base. In risky or out-of-knowledge-base situations, it hands the chat to the live team. The final approval can always stay with the boutique.

Does the AI make up stock and price?

No. The AI states the price and stock status only from your knowledge base. It does not invent a size, color, or stock detail it does not know; it says it does not know and hands off to the live team. Since stock is dynamic at a boutique, it leaves critical color/size confirmation to the team. This is the most important trust rule.

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 the source. When clear stock confirmation is needed, for example on the question "do you have L right now?", it hands the chat to the live team since that is out-of-system data.

Does it automatically reply to Instagram comments too?

The first step is WhatsApp and Instagram DM; these are live. Instagram comment automation rolls out gradually, subject to Meta approval, so we do not guarantee the fully automatic flow that moves a comment to a DM. In practice, you move incoming comments into a DM and continue the conversation there.

What happens to a DM that arrives at night?

The AI responds 24/7. To a "do you have this dress in M?" question that arrives at 2 a.m., a reply goes from the knowledge base within seconds; if suitable, it routes the customer to the product and to payment. When you open up in the morning, ready leads and answered questions are waiting for you.

Which channels does it bring together in a single inbox?

WhatsApp, Instagram DM, Facebook Messenger, Telegram, web chat, and email come together in a single inbox. Instagram comment automation rolls out gradually, subject to Meta approval; the first step is WhatsApp and Instagram DM.

Next step

If you haven't trained your assistant yet, start first with the how to train inTusell's AI article — the foundation of these operations is set up there. If you want to go deeper on the channel side, you can move to the Instagram and WhatsApp automation article, and to detail the selling-from-DMs flow, the DM sales automation article; you can see the Instagram boutiques solution page and the whole series from the all articles page.

To see how it'll work at your own boutique live, Get a demo or write directly to hello@intusell.com. In a 20-minute session, we'll open your inbox together and test the first response in the system.