An AI Assistant for Estate Agents That Qualifies Prospects and Wins Seller Leads

From your own material: listings, property data, energy performance figures, commission details and your FAQ on the process. Every source is read in, split into sections and stored with its heading and origin; the search over them combines a keyword comparison with a local feature calculation, whose rankings are merged. So it answers questions about living space, year of construction, location or availability from your offers and points to the right listing. Its answers stay bound to these sources: if it finds no supporting section, it usually does not guess but hands over to an agent.

Yes, as long as the document has a text layer. The knowledge base accepts files up to 10240 KB and splits them into overlapping sections so a passage does not end mid-sentence; a PDF is read through its existing text layer. A scanned sheet without a text layer deliberately yields nothing — there is no text recognition from the image, and the reason is shown as a message on the source instead of silently missing. For the question, at most five search hits plus your text blocks then go to the model, numbered, and sourced answers name the excerpts they rely on. For prices, terms or deadlines that have to be exact, the maintained question-and-answer pair is the better place: it goes out verbatim. More under knowledge base.

Not in the same instant, but without you doing anything. Website sources carry a refresh rhythm, seven days by default; it can be set from one day up to 365 days, and the value zero switches it off. The run happens at night. If a change should take effect sooner, trigger the read manually under Knowledge and then check the state of the source to see how many sections were produced. Each run writes a new version and switches over only at the end: if it breaks off, the previous state keeps answering, and a run that wrote nothing deletes nothing either. Five versions are kept. More under knowledge base.

It asks follow-up questions tailored to your business, for example about budget, buying or renting, the desired number of rooms, timeframe and financing status. Which fields are collected you define on the tool. So you do not receive an anonymous contact but a lead with context: name, address, phone and matter land in the mailbox of the business, with files uploaded beforehand attached. The assistant never sets an account or customer identifier itself and never states a result that did not come back. Where a conversation goes further than a form reaches, it hands over to a human and the transcript goes along. More under lead assistant.

It takes viewing requests; a viewing becomes firm only once you confirm it. The request runs through the appointment tool type and never unconfirmed: the proposal states place, time and kind of appointment in plain text in the chat, only the visitor's click creates the request, and once you confirm it in your view, the visitor receives a confirmation email, if they gave an email address. On request the assistant names free times from your stored kinds of appointment — time windows, duration, lead time and buffer — minus the appointments already requested or confirmed in XICBOT; it does not compare them with an external calendar, and a time it names remains a suggestion. A binding entry straight into your calendar only happens with a calendar connection set up in the Custom package. A request is only possible if its kind is known to your company, the lead time fits and the moment falls into an approved window; occupancy is checked under a lock, and a double click creates no second viewing. An hourly run sends the reminder for the confirmed appointment by email, if an address is on file. If nothing fits right now, the assistant takes a callback note with a preferred time instead. More at the booking assistant.

In the chat a request is created; it becomes an appointment only through your confirmation. Creating the request is a write operation and never runs through unconfirmed: the assistant presents the desired appointment as a proposal in plain text — what is to happen appears as its own sentence — and only the visitor's click creates the request. A request is only possible if its kind is known to your business, the lead time fits and the moment falls into an approved window; occupancy is checked under a lock. A double click creates no second request, because a one-time key made of conversation, tool and sorted input blocks it. Once you confirm the request in your view, it becomes an appointment, and if the visitor gave an email address, they then receive a confirmation email. The assistant enters appointments straight into your calendar only with a calendar connection set up in the Custom package; the calendar_booking adapter then writes the appointment into it after the visitor's click. Details under booking assistant.

The assistant checks occupancy under a lock: the check and the entry happen in one go, so a time slot is not given out twice. Against a double click there is a bolt in the database rather than in the program flow — the same request submitted twice does not create a second request. An appointment request becomes an appointment when your business confirms it. Without a calendar connection the assistant counts the appointments already requested or confirmed in XICBOT; what is only in an external calendar it does not see. With a calendar connection set up in the Custom package it reads free times through the calendar-availability form and writes the entry through the calendar-booking form; then the free times offered follow your calendar — including appointments that came in by phone or email. The check under a lock does not apply on this path: whether a slot taken in the meantime is rejected at booking is decided by your calendar. XICBOT sends each booking with an idempotency key by which your calendar can recognise a booking submitted twice.

Yes. When an owner gets in touch, the assistant captures property type, location, living space and year of construction in the conversation and hands a structured valuation request to your acquisition team. Which fields are asked for is your decision: a schema of your own carries up to twenty fields, the input is trimmed to that schema before execution, and if a required field is missing nothing is executed at all. What gets handed over is shown in plain text beforehand; the transfer writes and therefore requires confirmation. In this way one assistant serves both sides of the market — seekers and owners — from the same sources. More under assistant for real estate.

Yes. Through defined actions the assistant hands leads to your inbox, your CRM or your agent software — structured and with the conversation context. Ready-made forms exist for creating a customer record, querying a case, leaving a callback note and opening a ticket; if your system is not among them, it is connected through the general query of an external system. Every outbound connection runs over the same path with target checking, a fixed time limit and a size cap, and a stored access token cannot be read back afterwards. How permissions are set is covered under tool control. Handover to your inbox is available from the Start package; the connection to your CRM or agent software is part of the Custom package.

The real estate assistant with qualification, viewing and callback functions plus conversation analytics is part of the Pro package from 149 € per month net, plus a one-time setup from 2,900 € net. A viewing request from the chat counts as an appointment only once your office has confirmed it; the occupancy check and the creation run under the same lock. An assistant that only answers property questions and captures contacts is often already possible with the Start package from 49 € per month net and 990 € net setup. All details are listed under pricing. All services can be cancelled monthly; there is no minimum term.