Custom AI Chatbot Development

AI Chatbot for Real Estate

Property enquiries arrive at all hours and go cold fast. A chatbot that answers listing questions and books a viewing while the interest is live is straightforwardly valuable — provided it is built with the compliance constraints this industry has.

Discuss your project

Fair housing, before anything else

In the United States, the Fair Housing Act prohibits discrimination in housing on the basis of protected characteristics, and it prohibits steering — directing prospective buyers or renters toward or away from particular areas based on those characteristics. The prohibition applies to what your agents say and to what your software says on your behalf.

This matters for chatbots specifically because the questions that trigger it sound innocuous. "Is this a good area for families?" "What are the schools like?" "What kind of people live in this neighbourhood?" An unguarded model will answer those helpfully, and a helpful answer can constitute steering. Similarly, a qualification flow that asks about familial status, national origin or disability, or that routes enquiries differently on that basis, creates exposure.

So the constraint is designed in rather than added. Questions in these categories are not answered: the bot redirects to objective, published data sources and offers to connect the enquirer with an agent. Qualification questions are limited to what is legitimately needed — budget, timescale, finance status, property requirements — and never touch protected characteristics. The topic list and the exact redirect wording are agreed with you, and we would strongly suggest your broker or compliance counsel reviews them before launch.

Outside the US the equivalent constraints differ, and in the UK equality legislation and estate agency rules apply instead. Tell us your jurisdiction and we build to it.

What it handles

Listing questions

Price, size, rooms, tenure, service charge, parking, pets, availability — answered from your listing data rather than improvised.

Booking viewings

Against the real availability of the agent responsible for the property, with confirmation and reminders. The highest-value action it takes.

Routing to the right agent

By property, area or team, so an enquiry does not sit in a general inbox overnight.

Qualification, within limits

Budget, timescale, finance or mortgage status, whether they have a property to sell, and what they are looking for. Written to your CRM as structured fields.

Similar properties

Where the enquiry is about something already under offer, which is a frequent and easily salvaged situation.

Out-of-hours capture

Where much of the value is. Portal enquiries arrive in the evening and the agency that responds first tends to get the viewing.

Landlord and vendor enquiries

Separated from buyer and tenant enquiries at the start, since they go to different people and matter commercially.

What it connects to

  • Your CRM: Reapit, Alto, Street, Propertybase, Follow Up Boss, or GoHighLevel for agencies running on it.
  • Your listing feed, so property data is current rather than copied — a bot quoting a withdrawn price is worse than no bot.
  • Agent calendars for real viewing availability.
  • Portal enquiries from Rightmove, Zoopla, Zillow or your own site, all into the same flow.
  • Your website and WhatsApp, which in property is often where enquirers prefer to talk.

Common questions

Tell us what you need

Describe the problem and we will come back with scope, timeline, and a rate. No obligation to proceed.

Get in touch