How does a real estate agency use intusell? A daily operations guide

In the first article, you trained the intusell AI: you uploaded your knowledge base and your portfolio, marked your sales conversations, and configured the persona and response rules. Training was a one-time setup. Now the real work begins: how does a real estate agency use intusell — that is, how does a real estate agency's day-to-day use of intusell actually work? This article walks through, step by step, what the assistant you trained does in the field over a full workday — from the incoming DM to a property viewing, from follow-up to handing off to a human.

This article is the second part of the real estate section of our sector-by-sector "how to train your AI" series. The first part, how to train the intusell AI, covered the setup; this one covers turning that setup into daily operations.

Quick answer

A day in the flow

The typical day of an agency that has set up intusell is very different from before. In the old days, the agent would come in each morning and go through dozens of unread DMs and unanswered "how much is it?" messages one by one. Now, the requests that came in overnight are already answered, suitable listings are matched, and some viewing appointments are already created. The backbone of a day works like this:

The team is now occupied not with scanning messages but with conversations that genuinely require a decision — especially negotiation and closing.

Who is it for?

This usage model especially makes sense for agencies that:

• Receive heavy demand via Instagram and WhatsApp — those who can't keep up with dozens of "how much is it, is it available?" messages a day.
• Lose after-hours demand — agents who miss buyers because they respond late to listing questions coming in the evening and on weekends.
• Manage a large portfolio — those forced to do the right match by hand across hundreds of listings.
• Suffer from no-shows — agents for whom viewing appointments wasted by no-show buyers turn into lost time.

If you have a volume of demand that a single agent can't keep up with, intusell works like a senior real estate agent who meets that demand.

Incoming request: the customer asks about the portfolio, the AI suggests a suitable listing

The flow starts when the customer sends a message. Imagine someone writes via Instagram DM: "Looking for a 1+1 to rent around Beşiktaş, about 25 thousand." The AI reads this message, scans the portfolio you uploaded to your knowledge base, suggests listings that fit the customer's criteria, and steers toward a viewing.

There are two important boundaries. First: the AI does not invent a listing that isn't in the portfolio. On a "do you have a sea view in this budget?" question, if it isn't in the portfolio, it doesn't make up a listing; it says "we don't have that in our portfolio right now, but our agent can share similar options." Second: the AI responds in whatever language the customer writes in — for foreign buyers and investors, this is critical.

If you added the "ask for budget, area, and number of rooms before suggesting a listing" response rule during training, the AI clarifies the criteria first; the suggestion isn't random, it's based on the customer's real need. We separately explain how all these channels come together in a single inbox in the Instagram and WhatsApp automation article.

Portfolio matching and price: what the AI says and doesn't say

This is the most sensitive point for real estate. The AI does not invent a listing or a price. It matches only from the portfolio you uploaded to your knowledge base; it states the price only from the list price defined on that listing. It evaluates the customer's criteria across these axes:

On questions like negotiation, mortgage eligibility, appraisal value, or "will this price come down?", the AI does not invent a figure. It passes these topics to the agent, because they require negotiation and judgment. Likewise, if an area or type not in the portfolio is asked about, the AI steers to the agent instead of inventing a listing. This behavior prevents you from giving the customer wrong information and then having to correct it; this is the foundation of trust.

You'll find a detailed account of how the portfolio is uploaded, how listing descriptions are written into the knowledge base, and how response rules are built in the how to train the intusell AI article.

Property viewing appointment: slot, conflict, and duration

When the customer says "can I see it?", the appointment engine kicks in. The AI doesn't pull a time out of thin air; it looks at the three things you defined during training: the appointment type's duration (for example, "Viewing 45 min"), the agent's working hours, and whether that slot is busy. If it finds a suitable slot, it creates the viewing appointment.

The most critical protection here is conflict prevention: two appointments cannot be booked for the same time. Before creating an appointment, intusell checks your working hours and existing appointments; if a conflicting slot is requested, it doesn't open the appointment. Cancelled or missed appointments free the slot again in this check. This eliminates the problem agencies working with a manual diary often face — booking two buyers into the same time and letting both down.

Every appointment has a status, and the lifecycle is clear:

scheduled
  → confirmed
  → attended (showed up / viewing done)
or
  → cancelled
  → missed (no-show)

The customer can view, reschedule, or cancel their own appointment via the /manage-appointment/{token} link in the appointment message. So they don't have to call the agent for every reschedule, and the slot doesn't go to waste. We explain in detail how the viewing appointment logic merges with portfolio matching into a single flow in the property viewing appointment automation article.

Reminders and cutting no-shows

In real estate, a no-show buyer is expensive: a wasted viewing both eats the agent's time and means another buyer who could have taken that slot is lost. intusell reduces this with automatic reminders.

Two reminders are scheduled for every viewing appointment:

• 1 day before: A message along the lines of "You have a viewing tomorrow at [date time] for [address]."
• 2 hours before: A short reminder along the lines of "You have a viewing today at [time] — 2 hours to go."

The reminder goes out through the channel the customer wrote from; if that channel is unreachable, SMS takes over, and if that also fails, email. The customer doesn't need to install a new app. The message contains a one-tap cancel/reschedule link, so the buyer can let you know in advance if they can't make it.

If the buyer still doesn't show, you mark the appointment as missed; intusell automatically re-offers the freed slot to suitable WhatsApp customers among those interested or in follow-up, and triggers a follow-up flow. So a no-show becomes not a lost hour but a re-evaluated opportunity. Note that this is not a "waitlist": no managed queue is kept, just an opportunistic re-offer to suitable WhatsApp customers in follow-up.

Google Calendar: one-way sync

When a viewing appointment is created, it is optionally copied to Google Calendar too. The agent sees the appointments in their own calendar — for example, in Google Calendar on their phone. Rescheduling and cancellation are reflected in the calendar too.

This sync is one-way: intusell → Google Calendar. That is, intusell writes the appointment to the calendar, but a change you make by hand in the calendar does not flow back to intusell. Conflict checking is always done from intusell's own appointment book. Google Calendar is optional; appointments and reminders work even if you don't connect it.

Following up with the quiet buyer: proactive follow-up and CRM

In real estate, most leads dissolve among buyers who say "let me think about it" and disappear. A person decides over weeks, talking to many agencies in the process; the one who isn't forgotten wins. intusell doesn't forget these leads. A buyer who got listing information and went quiet receives a proactive follow-up message; interest is kept alive. Every conversation is logged into the CRM, so the customer's history, which listing they were interested in, and what stage they're at stay on record.

This way, when the agent sits down to operations in the morning, it's clear which buyer is hot and which is awaiting follow-up. There's no need to keep a manual reminder list or to dig through history asking "who said what?"

Handing off to a human: lock modes

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

In hybrid mode, the AI hands off a topic requiring figures — like negotiation or mortgage/valuation — or a situation it's unsure about, to the agent. At the moment of handoff, the full history of the conversation is in front of the agent; the customer doesn't have to explain from scratch. You can change the mode at any time — for example, ai_only during a busy listing period, human_only at a sensitive closing.

Channels and reports

intusell isn't tied to a single channel. All correspondence — WhatsApp, Instagram DM, Facebook Messenger, Telegram, web chat, and email — is gathered in a single inbox. You connect WhatsApp via QR in about 1 minute; this method requires no Meta approval. If you wish, you can also use the official WhatsApp Cloud API.

On the Instagram side, the first step is Instagram DM, which is approved. Instagram comment automation (automatic replies to comments under listings) opens up gradually, subject to Meta approval; in your agency this gate is controlled by a separate setting. So you start out with WhatsApp + Instagram DM and bring comment automation online as approval comes through.

On the operations side, how many requests came in from which channel, how many viewings were created, and how many leads are at which stage are reported in the panel. For product and pricing details, see the solutions and pricing pages.

What it isn't

To place intusell in the right category, let's clarify what it isn't:

• It's not a chatbot. It's not a flow bot that answers from preset templates; it's a fully autonomous AI sales assistant that works with the portfolio and sales techniques you trained.
• It's not a portfolio/listings platform. It doesn't provide listing inventory; it uses the portfolio you upload.
• It's not a valuation or appraisal tool. It doesn't assess value or estimate prices; it leaves those decisions to the agent.
• It's not a real-estate-specific priced product. The pricing model is based on messages and voice minutes; it doesn't change by sector. The appointment module can be enabled on any plan.

So you don't start with the wrong expectation, let these boundaries be clear from the outset.

Frequently asked questions

Does the AI match listings from the portfolio?

Yes. The AI asks for the customer's criteria such as budget, area, number of rooms, and square meters; it suggests suitable listings only from the portfolio you uploaded to your knowledge base. It does not invent a listing or a price that isn't in the portfolio; when unsure, it hands off to the agent.

Does the AI quote prices?

Only the list price defined in your portfolio. On topics like negotiation, mortgage eligibility, or valuation, it does not invent a figure; it passes the topic to the agent. Instead of making up a price it doesn't know, it says "our agent will clarify this."

How is a property viewing appointment created?

The AI creates a viewing appointment based on the agent's working hours and busy slots. A double booking for the same time is blocked by the system. Automatic reminders go out 1 day and 2 hours before; the customer manages their own appointment via the /manage-appointment/ link.

What happens with a no-show buyer?

When an appointment is marked "missed", that slot frees up again and is automatically re-offered to suitable WhatsApp customers in follow-up; a follow-up flow is triggered. So a missed viewing turns into a re-evaluated opportunity.

Can a customer be connected to a human?

Yes. In hybrid mode the AI runs the normal flow and escalates the conversation to the live team when needed. In human_only mode all conversations go straight to the agent, and in ai_only mode the AI handles everything. You can change the mode at any time.

Do appointments show up in Google Calendar?

Yes. When a viewing appointment is created, it is copied to Google Calendar; rescheduling and cancellation are reflected too. The sync is one-way (intusell → Calendar); the agent sees the appointments in their own calendar.

Can it respond to foreign buyers?

Yes. The AI responds in whatever language the customer writes in; no extra configuration is needed. Replying to investors and buyers from abroad in their own language works the same way regardless of channel.

Next step

If you haven't trained your assistant yet, start with the how to train the intusell AI article first — the foundation of this operation is built there. If you want to go deeper on the channel side, you can move on to the Instagram and WhatsApp automation article, and for the detail of the appointment engine, the property viewing appointment automation article. You can see sector-specific usage on the real estate solution page, the plans on the pricing page, and the whole series on the all articles page.

To see live how it would work at your own agency, request a demo or write directly to hello@intusell.com. In a 20-minute session, we open your inbox together and test the first portfolio match and viewing appointment in the system.