Restaurant AI training: a step-by-step guide

When the evening service heats up, the phone does not stop: "Do you have a table for 4 tonight?", "Are there gluten-free options?", "How much is takeaway, and how long does it take?", "Do you have parking?". With the kitchen slammed, someone has to watch the phone, Instagram DMs, and WhatsApp all at once. Most of the time, they cannot; the message goes unanswered, and the customer books with the competitor down the street.

inTusell takes over this traffic. But to do so, it first needs to learn about your restaurant, your menu, and your way of talking. This article explains how a restaurant or cafe trains the inTusell AI from scratch, step by step. This is the restaurant chapter of our sector-based "how to train your AI" series, and it is the cornerstone article of the series.

Quick answer

Why does training matter?

inTusell is not a canned 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. Good front-of-house staff do not start on day one without knowing the menu by heart, either. Training enables the AI to do two things correctly: give the right information (your menu, real prices, allergens) and give it the right way (your restaurant’s tone, your way of welcoming guests).

An untrained assistant either gives overly generic answers or guesses about something it does not know. In a restaurant, guessing is expensive: wrong allergen information is a health risk, and a made-up price creates distrust in the customer who sits down at the table. A well-trained assistant stops when it does not know and connects to the team. This is the strongest trust message you can build.

Who is it for?

This guide is for restaurants and cafes whose incoming message traffic is getting busy and who answer the same questions over and over again:

• À la carte restaurants, cafes, bistros, brunch spots, pizzerias, and takeaway businesses
• Teams receiving dozens of reservation and order questions a day via Instagram and WhatsApp
• Businesses in tourist areas that communicate in multiple languages with foreign guests
• Operators who do not want to pull someone away from the kitchen to answer the phone during the rush

You do not need a technical team. All of the steps below are completed from sections in the panel, without writing any code.

The structure of training: 5 core steps + 2 continuous steps

Dividing the training into two groups makes things easier. The first 5 core steps get the assistant operational; these steps are the part of the setup that is done once. The following 2 continuous steps (reviewing and turning fixes into rules, and opening the channels) are the ongoing part, where you sharpen the assistant as you use it. You will find all of them in order below.

1. Upload the knowledge base

The foundation of training is the knowledge base (RAG). In the panel’s My business › Knowledge › Knowledge Base section, you upload your restaurant’s information. Every time the AI generates a response, it automatically searches these sources and uses only the information written there.

Supported source types:

Every file you upload is automatically chunked and made searchable via pgvector. When you upload your menu, and a customer asks "Is there a vegan main course?", the AI finds the right section and responds.

What must be uploaded in a restaurant: the menu and prices, allergen and ingredient information, opening hours and address, reservation and takeaway conditions, venue details such as parking/children/pets, and the most frequently asked questions. Once these six headings are uploaded, the answers to the most frequent questions are ready.

2. Connect the menu and prices

In the first step you uploaded the general texts to the knowledge base; in this step you focus on keeping your actual product backbone (the current menu and prices) accurate. In a restaurant, there is no external catalog integration like in tourism; your menu is the knowledge base itself. That is why keeping a single "current menu" source is critical.

The practical setup looks like this:

• Upload the current menu as a single PDF or Excel file; remove old/conflicting files.
• Collect seasonal or daily-changing prices in a separate short file so they are easy to update.
• Write conditions such as the takeaway surcharge, minimum basket amount, and delivery area in the same place.

The critical point here is this: the AI does not invent prices. It only answers from the menu you upload. When asked about an item not on the menu or a price it is unsure of, it does not estimate; it says it does not know and offers to connect to the team. Likewise, stock is not real-time: you tell the AI about the items that have sold out for the day (as a short note or a response rule), and it then avoids recommending that item and offers an alternative.

When the menu changes, the only thing you need to do is add the current file to the knowledge base and remove the old one; the AI uses the new price once the file is processed. You can see all the capabilities of the knowledge base on the Solutions page.

3. Set the persona and tone

You taught the AI what to say in the first two steps; now you will determine how it says it. There are two settings in the panel:

• Assistant name (ai_persona_name): The name it will introduce itself to the customer with. Most businesses use a warm name aligned with the brand or a real host’s name.
• Tone (ai_tone): Whether it speaks warmly and casually, in a sophisticated and calm manner, or quickly and practically.

The tone of a family restaurant and a fine-dining venue will not be the same. The former might be warm, witty, and inviting; the latter measured, polite, and selective. A neighborhood cafe uses relaxed, everyday language. This setting is reflected in the AI’s messaging language on every channel.

A note on multiple languages: The AI responds in whatever language the customer writes in. If you are in a tourist area, when a foreign guest writes in English, you do not do anything separate; the assistant automatically detects the language and replies in that language while preserving the tone.

4. Define the response rules

The persona defines "who it is," and the response rules define "how it behaves." This is where you transfer your guest-welcoming discipline to the AI. With the AI Manager Chat, you add rules by writing in plain language, just as you would instruct a teammate.

Typical rules for restaurants:

• "On a reservation request, first ask the party size, date, and time."
• "When asked about an allergy, read the allergen information from the menu clearly; never guess 'it does not contain it'; if unsure, say the kitchen will be consulted."
• "On a takeaway request, state the minimum basket amount and the delivery area."
• "If asked about an item not on the menu or a price you are unsure of, do not make it up; connect to the team."

Guessing on an allergen question is the most dangerous mistake you can make in a restaurant. The "consult the kitchen if unsure" rule turns the AI from a machine that makes something up for every question into a genuinely reliable host.

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.

5. Teach it from past calls

This is the step that takes the training from "good" to "specific to your restaurant." In the panel, you upload the voice recordings of your past phone calls (MP3, MP4, WAV, M4A) and mark each one as Won or Lost. In a restaurant, "won" means a call that turned into a reservation or an order.

The system uses these recordings in two ways:

In other words, the AI learns how your best host turns a "we are full tonight" situation into an alternative time slot and how they guide an undecided customer, and it applies the same approach in similar situations. Personal data is handled too: uploading requires explicit consent, and phone, email, ID and card numbers are masked in the transcript before processing.

This step is not mandatory, but do not skip it. The knowledge base teaches the AI "what" it knows; the call recordings teach it "how you welcome guests and sell." When the two are combined, the assistant truly resembles a senior team member.

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

The first five steps get the AI operational; from there on you sharpen it for your restaurant. You check replies in the AI Test screen by asking questions as a guest would, and in Conversations on real chats.

When you see a wrong or missing answer, make the fix permanent. Say the AI quoted a dessert at an old price: remove the old file and add the current menu to the knowledge base. If it relayed a promotion wrongly or did not ask the party size before booking, write a rule in AI Rules, switch on a fitting ready rule pack in the Behavior Library, or tell the AI Manager Chat in a plain sentence ("ask the party size before booking"). In a period when you want to see every reply before it goes out, put the account in Full approval mode or a single conversation in Approval mode.

The Label Manager is a separate job: a customer satisfaction reply, the outcome of a handed-off conversation, a won/lost classification and a label a team member adds by hand land there. You approve, reject or edit; 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.

7. Open the channels (ongoing step)

Once the training is ready, you put the assistant in front of customers. inTusell brings all channels together in a single inbox: WhatsApp, Instagram DM, Instagram comments, Telegram, and web chat.

Channel activation methods:

• 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 press "QR ile Bağlan" (Connect with QR) and scan the code on your phone via WhatsApp › Settings › Linked Devices › Link a Device; if you have no second screen, "Link with phone number" gives you an 8-character linking code. The number stays the same and no Meta Business approval is needed. The official WhatsApp line (Cloud API) opens after Meta approval; today you connect with QR or a linking code.

Once Instagram is connected, DM replies are already on. Comment replies have their own switch on the Instagram card ("Instagram comments"), which is on by default; if you want to automate only DMs first, turn it off and switch comments on when you are ready. If you connected Instagram before September 24, 2026, you need to reconnect it once for comments.

Account-wide there are three AI modes. Intern (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 case needs a person, such as a large group, a private event or a complaint, it hands the conversation to your team; the handoff lands on the Decisions screen with the full history. For details on Instagram and WhatsApp automation: Instagram and WhatsApp automation.

There is a protection layer, but it is not a "blocker"

In restaurant content, allergen and health-related questions are sensitive. In inTusell, the real control is the instructions that constrain the AI so it does not produce wrong information in the first place: the assistant does not claim an ingredient is "absent" if it is not written on the menu. On top of that, an output filter (a pattern scan plus a second-model check) scans replies for misleading health claims and flags them; it does not block everything. So the correct framing is this: the AI is constrained, and the filter scans and flags, but the real weight of safety is carried by your response rules and the accuracy of your menu information.

How long does training take?

How long it takes depends mostly on whether your documents are ready; if your menu is already digital, the first upload is short. The steps of a working setup:

1. Uploading the first files to the menu and knowledge base
2. Separating out the current price file
3. Persona, tone, and first response rules
4. Connecting the channels

But there is no moment where "training is done." 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, the assistant sharpens to fit your restaurant; 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 the wrong expectation leads to the wrong setup.

• It is not a static menu bot. It is not a tool that shows a few pre-written answers in sequence; it is an assistant that understands every question asked and generates a dynamic response from the knowledge base.
• It is not a chatbot tied to a rule tree. There are no "press 1, press 2" menus. The customer writes freely, and the AI understands the intent.
• It is not a real-time stock/POS system. You tell it about sold-out items and price changes; it does not make things up, and it asks when it does not know.
• It does not announce an empty table to other guests. It does not run a queue like "I have put you in line and will call when a spot opens." Instead, a guest who went quiet gets at most 3 follow-up messages within business hours (next section).
• It is not a table plan or table assignment tool. It records the reservation by time; you decide on the floor which table the guests get.

In short: not a bot that gives canned answers, but a welcoming and sales assistant that represents your restaurant to the extent that you train it.

After training: reservations, reminders, and proactive follow-up

After you train the assistant, two modules come into play. The first is the appointment engine: you define your opening hours and reservation length; the AI collects the date, time, party size and any note on WhatsApp or Instagram. What happens next depends on your account: if the AI booking tools are on, it checks your working hours and booked times, books the free slot itself and writes the party size into the note; if not, it passes the request to your team with those details, and you confirm the time or the guest picks a free slot on your online booking page. To see which applies, ask for a booking in AI Test. A second reservation at the same time is blocked; if you take several tables at the same time, you define that service as a group session with capacity. On paid plans an automatic reminder goes out 1 day and 2 hours before, so fewer guests fail to show; the guest manages their own reservation via the /manage-appointment/{token} link, cancelling or rescheduling if needed. Takeaway is a separate flow: if your menu is set up as products in the panel and Payment tracking is on, the AI confirms the items and amount and opens the order. Details: restaurant reservation automation.

The second is proactive follow-up (CRM): a guest who left a conversation half-finished gets at most 3 follow-up messages written by the AI; they go out only within business hours on WhatsApp, Instagram or Telegram and stop when the guest replies, books, or asks not to be contacted. You will find how to run the assistant you trained in daily service in the usage article of the series: how a restaurant uses inTusell.

Frequently asked questions

How long does restaurant AI training take?

A working setup comes down to these steps: uploading the menu and prices to the knowledge base, setting the persona and tone, and a few response rules. 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 event; it is continuous.

Do I need technical knowledge to train the AI?

No. All training is done from the panel; no code, API key, or developer is required. You upload your menu to the knowledge base as a PDF/Excel file, choose a persona, and write response rules in plain language. You connect Instagram through Meta login and WhatsApp with a QR code or a linking code.

Will the AI give a wrong price or mention a dish that does not exist?

No. The AI only answers from the menu and prices you upload to the knowledge base. When asked about an item not on the menu or a price it is unsure of, it does not make it up; it says it does not know and hands off to the team. Not inventing prices or stock is the most important trust rule.

What happens for an item that has run out?

You enter the items that have sold out for the day as a response rule or a short knowledge-base note; the AI will not recommend that item and offers an alternative instead. The AI is not a real-time stock system, so you tell it about sold-out items. When unsure, it does not guess; it asks the team.

Will the AI use the new menu when the menu changes?

Yes. When you add the current menu to the knowledge base as a new file, the AI uses the new prices and items once the file is processed. Removing the old file is enough to avoid any conflicting information.

Does it reply to Instagram comments automatically as well?

Yes. Instagram comment replies are live and the "Instagram comments" switch on the Instagram card is on by default; the AI writes one public reply per comment. DM replies are already on once Instagram is connected. If you connected Instagram before September 24, 2026, you need to reconnect it once for comments.

Next step

You have trained your assistant; next comes using it in daily service. The next article in the series explains how to run the inTusell you trained during a real evening service: inbox management, the reservation flow, takeaway order routing, and team handoff. Continue straight from there: how a restaurant uses inTusell.

You can read this series for other sectors too: you will find a similar setup in automotive AI training for automotive, tour agency AI training for tourism, and clinic AI training for health.

If you would like to see it live before starting the setup, let’s open your panel together in a short session via Request a demo, or write to hi@intusell.com. You can find all the capabilities of the restaurant solution on the restaurant solution page, package and quota details on the pricing page, and other guides in the all articles list.