Real estate chatbot development for lead capture and showing scheduling
A real estate chatbot answers inquiries about your listings, collects what an agent needs to qualify the lead and books a showing, on your website and messaging channels. Goldenroz builds it on your listing data and your CRM, with fair housing limits written into its rules and a handoff to the right agent. Projects start at $25,000, fixed price per phase.
From $25,000, fixed price per phase
Updated 2026-11-14. By Shai Goldenberg
What usually goes wrong
- Inquiries at night and on weekendsBuyers and renters browse listings after work. An inquiry sent at ten in the evening gets a reply the next day, after the person has written to three other brokerages.
- Leads with no contextA portal lead arrives in the CRM as a name and a phone number. The agent starts from zero on budget, timing, financing and area.
- Showing times by phone tagThree calls and two texts to agree a viewing time. Popular rentals lose applicants to the building that confirmed first.
- Answers that create legal exposureAn untrained assistant, human or automated, describes who lives in a neighborhood or suggests where a family would fit. That is the kind of statement fair housing law prohibits.
What is included
- Listing Q&AAnswers about price, size, availability, fees, pet policy and features taken from your listing data. If a field is empty, the bot says it will ask the agent.
- Lead capture and qualificationContact details, timing, price range, financing or income documents status and must-haves, asked in conversation and applied the same way to every person.
- Showing schedulingOpen slots read from agent or leasing calendars, the viewing booked and confirmed, and reminders sent before it. Reschedules update the calendar.
- CRM integrationThe lead, the transcript and a summary written to your CRM and assigned by your routing rules: listing agent, area team or round robin.
- Fair housing guardrailsA written list of topics the bot declines, tests that try to make it steer, and logs your compliance lead can review.
- Handoff and fallbacksTransfer to an agent on request, on offers and on negotiation. Fixed replies go out if the model fails, and the lead is still saved.
How a real estate chatbot qualifies a lead without wasting it
Property decisions take weeks or months, and most people who write are early. The bot answers the question that brought the person in first, then asks a few things an agent would ask: when they plan to move, the price range, whether financing is arranged, which areas and what they cannot live without.
The answers go to the CRM as structured fields, so an agent sees at a glance who wants a showing this week and who is six months away. The second group is kept, tagged and followed up by your existing process.
Listing data has owners. Content from an MLS feed comes with display and usage rules set by that MLS, and your license determines what a bot may show. We confirm the data source and its terms during scoping. Broader automation for brokerages and property managers is described under AI for real estate.
Fair housing: what the bot must never do
The federal Fair Housing Act prohibits discrimination in housing based on race, color, national origin, religion, sex, familial status and disability. Many states and cities add further protected classes, such as source of income. Steering, meaning guiding people toward or away from areas or buildings because of a protected characteristic, is prohibited whether a person or a program does it.
The bot is therefore built with fixed limits. It does not ask about protected characteristics, does not filter or rank listings by them and does not describe the people in a neighborhood. Questions about schools, safety or who lives nearby get a neutral reply that points to public sources. Every inquirer gets the same qualification questions and the same access to showings.
Goldenroz builds and documents the controls. We are not a law firm, and your counsel or compliance officer reviews and approves the bot's scripts and refusal list before launch.
Where the bot lives: site, messaging and the CRM
Most inquiries start on a listing page, so the first channel is usually a chat widget that knows which property the visitor is viewing. See website chatbot development for that channel.
Integration targets are the systems you already run: a CRM such as Salesforce, HubSpot or a real estate CRM with an API, agent calendars and, for rentals, your property management system. Process and timelines follow the parent AI chatbot development service.
How the work runs
Scoping call
Before the projectWe review real transcripts, pick the intents worth automating and agree what the bot must never do. You get a fixed price.
Prototype
About 1 to 2 weeksA working bot on the top few intents, tested against your past conversations in a private channel.
Production build
Roughly 4 to 8 weeksSystem integrations, fallbacks, handoff, logging and channel setup. The range depends on integrations and on WhatsApp account approval.
Limited launch
At launchThe bot handles a share of conversations or selected hours first. Your team reviews transcripts daily.
Widen
After launchNew intents are added in order of volume, each tested against the conversation set.
What it costs
Each phase has a fixed price agreed before work starts. Model usage and WhatsApp messaging are billed by the providers to your own accounts.
- Support or ordering botFixed price per phaseFrom $25,000
- Multi-channel or multi-brand platformsScoped per project$100,000 and up
- Scoping callEnds with a written scope and a price$0
- Model and WhatsApp usageBilled to your own accountsPaid to the providers
Who it is not for
- Solo agents and budgets under $25,000. The chat feature in your CRM or portal is the better fit.
- Tenant screening or approval decisions. Those stay with people.
- Bots that give valuations, legal advice or mortgage advice.
Who does the work
Shai leads the technology side: business software, SaaS and mobile apps, payments and escrow systems, Postgres security, AI agents built with Claude Code and MCP, and IT and infrastructure projects with senior infrastructure engineers.
Questions buyers ask
How much does a real estate chatbot cost?
Projects start at $25,000 at a fixed price per phase, agreed after a free one-hour scoping call. Model usage and hosting are billed to your own accounts.
Can the bot schedule showings on its own?
Yes, within rules you set. It reads open slots from the calendars you connect, books and confirms the viewing and notifies the agent.
Which CRM does it work with?
Any CRM with a usable API. We confirm the fields, routing rules and duplicate handling in scoping.
Is the bot fair housing compliant?
Compliance is the responsibility of the brokerage or housing provider, not of a piece of software. We build the limits, the tests and the logs that support it and document them. Your counsel approves the content before it goes live.
Does the bot replace agents?
No. It handles first replies, facts and scheduling. Pricing advice, offers, negotiation and anything that needs a license go to an agent, with the conversation attached.
Guides on this topic
- Chatbot cost depends on channels, integrations, AI or scripted logic, usage and upkeep. Compare a platform subscription with a custom build and plan a budget.
- What an AI agent costs to build and to run: the five cost drivers, project shapes by effort, and a worked running-cost example. See where your project lands.
- Nine steps to build a WhatsApp chatbot on the official Cloud API: account, number, webhook, AI layer, handoff, templates and launch. See the full checklist.
More for real estate
Chatbots by channel and use case
- AI chatbots
- Appointment booking bots
- Chatbots for banking and insurance
- Customer service chatbot development
- Chatbots for ecommerce
- Enterprise chatbot development
- Chatbots for healthcare
- Instagram and Messenger chatbots
- Microsoft Teams and Slack bots
- RAG and knowledge base chatbots
- Telegram bot development
- Website chatbot development
- WhatsApp Business API integration
- WhatsApp chatbot development
- Chatbots
Talk to the person who will do the work
One hour, no sales team. You talk to Shai Goldenberg, the CTO, about your systems or your product, and you leave with a clear next step and a price range.