Tour agency AI training: a step-by-step guide

When the season opens, a tour agency’s inbox fills up with the same questions: "Is the visa included in the Umrah price?", "Is there a child discount on the Cappadocia tour?", "Do I get my money back if I cancel?". In an operation where the same twenty questions are repeated a hundred times a day, the team spends its time churning out copy-paste answers rather than actually closing sales. And when a foreign tourist writes in English or Arabic, the response is delayed even further.

inTusell takes over this load. But to do so, it first needs to learn about your agency, your tours, and your sales style. This article explains how a tour agency trains the inTusell AI from scratch, step by step. This is the tourism 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 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 simple chatbot. At a tour agency it behaves like a senior salesperson. A senior salesperson does not know your agency on day one either. Training makes the AI do two things correctly: give the right information (your tour’s terms, real prices) and give it the right way (your sales style, your tone).

An untrained assistant either gives overly generic answers or guesses about something it does not know. In tour sales, guessing is expensive. Wrong visa information or a made-up price loses the customer and undermines trust at the same time. A well-trained assistant, on the other hand, stops when it does not know and hands the conversation to your team.

Who is it for?

This guide is for tour agencies whose inboxes are getting busy and who answer the same questions over and over again:

• Agencies selling Umrah, Hajj, cultural, holiday, domestic, and international tours
• Operations teams receiving dozens of questions a day via Instagram and WhatsApp
• Agencies that need to communicate in multiple languages with foreign tourists
• Those who want to relieve their existing team rather than increase headcount during the season

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 Knowledge Base section, you upload all of your agency’s textual information. Every time the AI generates a response, it automatically searches these sources; tour terms, visa and cancellation details come from here, while prices are read from the catalog’s matrix.

Supported source types:

Word files, images and plain text work too (up to 50 MB per file); a website scan is refreshed weekly, and you can import the last 100 posts from your Instagram profile. Every file you upload is automatically chunked and made searchable. An Excel or CSV price list is read here as a document; it does not load prices into the tour engine. If you upload an Umrah program PDF and a customer then asks "How many nights do we stay in Medina?", the AI finds the right paragraph and responds.

What must be uploaded in tourism: tour terms, visa requirements, cancellation/refund policy, deposit rules, baggage allowances, and the most frequently asked questions. With these six headings in place, the AI answers the most frequent questions from your own text.

2. Connect the tour catalog

The knowledge base explains "what you sell and the terms"; the tour catalog provides "current prices." inTusell’s tour/booking module (beta) pulls your catalog through the KolayTurum integration (tours, hotels, the price matrix and seats already sold in KolayTurum); if you don’t use KolayTurum, you import packages from your website or enter them in the panel.

The price matrix is three-dimensional: departure point × hotel class × room type. Child price (according to the age threshold you define), infant price, single supplement, and deposit rules are also included in the matrix. The currency is USD by default.

The critical point here is this: the AI never invents a price. It only quotes from the price matrix. For a combination that is not in the matrix (for example, an undefined departure-hotel pairing), it does not estimate a price; instead, it hands the conversation to your team, and the handoff lands on the Decisions page. This is the behavior that builds the most trust in tour sales.

If KolayTurum is connected, the catalog syncs automatically every night (around 05:00 Turkey time), so prices stay fresh without the need for manual updates. We have a separate article on connecting the catalog, the price matrix, and XML details: tour catalog and KolayTurum/XML integration.

If you do not use KolayTurum, that is not a problem: upload your tour information to the knowledge base as Excel or CSV and the AI answers questions with it. Exact quotes, seat holds and payment run from the catalog; import it from the tour pages on your website or enter it in the panel. You can see all the capabilities of the tour module 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: The name it will introduce itself to the customer with. Most agencies use a real consultant name from the team or a name aligned with the brand.
• Tone: Whether it speaks warmly and casually, formally and reserved, or quickly and concisely.

The tone of an agency selling Umrah and one selling adventure tours will not be the same. The former might be respectful and reassuring, the latter energetic and excited. 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. When a foreign tourist writes in English, you do not have to do anything extra; the assistant automatically detects the language and replies in that language while preserving the tone. Fixed system messages go in Turkish to Turkish speakers and in English to everyone else.

4. Define the response rules

The persona defines "who it is," and the response rules define "how it behaves." This is where you pass your sales discipline on to the AI. You add rules through the AI Manager Chat in plain language, just as you would brief a teammate.

Typical rules for tour agencies:

• "Before quoting a price, ask how many people are going, which dates, and which hotel class they want."
• "If the customer is undecided, remind them of the departure guarantee and the early-booking advantage."
• "When asked about cancellation/refund, read the policy clearly from the knowledge base without adding interpretation."
• "If asked about a combination not in the price matrix, do not make it up; connect to the live team."

Quoting a price without doing needs discovery is the most common mistake in tour sales. The "ask about needs before quoting" rule turns the AI from a machine that spits out a price with a single question into a consultant that guides the customer to the right package.

To compare two 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 exposures and the win rate. Today only the tone changes; the content and the rules stay the same.

5. Teach it from past sales calls

This is the step that takes the training from "good" to "specific to your agency." In the panel, you upload the voice recordings of your past sales calls (MP3, MP4, WAV, M4A) and mark each one as Won or Lost.

The system uses these recordings in two ways:

In other words, the AI learns how your best salesperson turns the "the price is too expensive" objection around, how they convince the customer, and applies the same approach in similar situations. On the KVKK side: uploading recordings 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 sales recordings teach it "how you sell." When the two are combined, the assistant truly resembles a senior salesperson.

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

The first five steps get the AI operational. What follows is the ongoing part that fits it to your agency over time. You review replies in AI Test and in Conversations. Say the AI gave the wrong age range for the child price: the age threshold is not fixed, it is the value you define in the price matrix, so you correct that row. If a tour term is missing or wrong, you add the fact to the knowledge base or write a rule in AI Rules. You can switch the ready rule packs in the Behavior Library on or off, and give the AI Manager Chat a plain-language instruction (for example, "answer visa questions with the knowledge base text, otherwise hand off to the team").

The Label Manager is something else: a customer satisfaction reply, the outcome of a handed-off conversation, a won/lost classification and a team member’s manual label land in its queue. You approve, reject or edit them; corrections are kept as a quality record, but they do not change how the AI writes replies today. Live behavior changes through rules, the knowledge base and the catalog.

In the first weeks, we recommend a short daily look at the replies. For a period when you want to see every reply before it goes out, put the account in Full approval or a single conversation in Approval mode.

7. Open the channels (continuous step)

Once the training is ready, you put the assistant in front of customers. inTusell brings all channels together in a single inbox: Instagram DM, Instagram comments, WhatsApp, 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.
• WhatsApp: you link it with a QR code or with an 8-character linking code sent for your phone number; your number stays the same, your phone keeps working, and no Meta Business approval is needed. The official WhatsApp line (Cloud API) opens after Meta approval; today you connect with a QR code or a linking code. The AI works only in one-to-one chats and never replies in WhatsApp groups.

You control each channel separately. Once Instagram is connected, DM replies are already on. Comment replies have their own switch on the Instagram card: "Instagram comments" (on by default). For example, you can switch it off, automate only DMs first and keep comments manual, then switch it back on when you are ready. If you want the AI to stop answering a channel altogether, turn that channel off in the channel list in the AI settings. There are three account-wide working modes (My business › Instructions › AI Settings › "Advanced AI Settings"): Intern (default) sends replies itself and asks you before a cancellation or refund; Senior also handles cancellations and refunds; in Full approval WhatsApp, Instagram and Telegram replies wait for your approval. New accounts start as Intern. When the AI is unsure or a person is needed, it hands the conversation to the team, and the handoff lands on the Decisions page. You can switch a single conversation to Approval, Shadow or Paused. For details on Instagram and WhatsApp automation: Instagram DM and WhatsApp automation.

How long does training take?

How long it takes depends mostly on how ready your documents and catalog are. The steps of a working setup:

1. Uploading the first files to the knowledge base (quick if your existing PDFs are ready)
2. Connecting the catalog: with your KolayTurum credentials, a website import or by hand
3. Persona, tone, and first response rules
4. Connecting the channels

But there is no moment when "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 AI Rules, the assistant settles into your agency. Uploading past sales recordings and running a tone A/B test (beta) are also ongoing improvements.

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 FAQ page. It is not a tool that shows 20 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 tool that estimates prices. In the tour module (beta), it only quotes from the matrix; it does not make prices up.
• It is not an intermediary that becomes the seller in your place. In tour sales, the agency is always the seller; inTusell does not become a party to the payment. Payment is collected via bank transfer/IBAN (no integration required; your team approves the receipt) or, if iyzico is connected, through the card payment link the AI sends.

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

Frequently asked questions

How long does tour agency AI training take?

A working setup comes down to these steps: uploading the knowledge base, connecting the catalog, setting the persona and tone, and a few response rules. How long it takes depends mostly on how ready your documents and catalog 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 PDFs/Excel files to the knowledge base, 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 incorrect or made-up tour prices?

No. In the tour module (beta), the AI only quotes from the price matrix in your tour catalog. It does not invent a price for a combination that is not in the matrix; instead, it hands the conversation to your team, and the handoff lands on the Decisions page. This is the fundamental rule of price reliability.

Is my data safe under KVKK?

Data is separated per agency, connections are encrypted, and personal passenger fields are stored encrypted in the database. At the payment step your customers receive your own KVKK notice link, and contract acceptance is recorded with a SHA-256 digest. You can download your data from the panel.

How do I train the AI if I do not use KolayTurum?

You can add your tour information to the knowledge base as Excel/CSV, PDF, Word or a website scan, and the AI answers questions with it. Exact quotes, seat holds, and the payment step run from the tour catalog, which you build with KolayTurum, by importing the tour pages on your website, or by entering packages in the panel.

Will the AI use the new prices when tour prices are updated?

Yes. If KolayTurum is connected, the catalog syncs automatically every night (around 05:00 Turkey time), keeping the price matrix current; for an urgent change, "Sync now" pulls it right away. If you entered packages by hand, you update the price matrix in the panel, and the AI reads the new row in its next quote. A price list you upload to the knowledge base is read only as a document; quotes come from the matrix.

Next step

You have trained your assistant; next comes using it in daily operations. The next article in the series shows how the inTusell you trained runs during a real season: inbox management, quote tracking, the booking flow, and team handoff. Continue straight from there: how a tour agency uses inTusell.

If you would like to see it live before starting the setup, use Request a demo and we will open your panel together in a short session, or write to hi@intusell.com. For package and quota details, you can check the pricing page, and for other guides, browse the all articles list.