Fixed quote after a free call

An AI chatbot for real estate agents that sticks to your listings and your rules

We build an AI assistant for your website, WhatsApp or phone line that answers questions from your live listings and your agency's approved answers, books viewings and valuation appointments and captures messages out of hours. It says it is automated, treats every enquirer the same and hands anything about price advice, mortgages, legal terms or a complaint to a person. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

What a real estate AI assistant should and should not do

An agency gets the same questions all day: is it still available, what are the bills, are pets allowed, how do I book a viewing, what are your fees, how long does a sale take. Each one pulls a negotiator off the phone with a serious buyer or landlord.

A generic chatbot makes things worse if it guesses. A real estate AI assistant has to answer only from live listing data and wording the agency approved, never steer people by protected characteristics and never give the kind of advice a licensed agent, lender or lawyer should give.

What we build

What our AI chatbot for real estate includes

Answers from live listings

Price, availability, rooms, bills, parking and pet policy pulled from your CRM or listing feed, not from memory.

Approved agency answers

Fees, process, referencing steps and opening hours written and signed off by the agency.

Viewing and valuation booking

Books from approved slots or creates a request for the right branch.

Same treatment for everyone

No questions about protected characteristics and no steering; rules are tested before launch.

Clear hand-off

Price advice, mortgage, legal or complaint topics go to a named person with the conversation attached.

Transcript review

A simple admin view and a weekly list of questions the assistant could not answer.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Question asked

    A visitor asks on the website, WhatsApp or phone and is told it is an automated assistant.

  2. 02 Automated

    Answer from your data

    The assistant answers from the listing feed and approved answers and links to the listing.

  3. 03 Automated

    Booking captured

    Viewings and valuations are booked or sent as requests to the branch.

  4. 04 Negotiator or PM review

    Staff follow up

    Negotiators confirm requests and reply to anything the assistant could not answer.

  5. 05 Agent or broker decides

    Advice

    Price, mortgage, legal and complaint questions are handled by an agent or broker.

How it behaves

How the AI assistant behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What the enquirer sees

  • A clear note that the assistant is automated
  • Answers from the live listing with a link
  • Viewing or valuation slots to choose from
  • A person whenever they ask for advice or want one

What negotiators see

  • Booking requests with the conversation attached
  • Hand-offs for advice, complaints and unclear questions
  • A weekly list of unanswered questions

What the automation does

  • Retrieves listing data and approved answers
  • Refuses advice and steering, then hands over
  • Logs every conversation

Edge cases and fallbacks

Listing data is out of date
The assistant only uses the current feed; withdrawn listings are answered with approved wording.
Enquirer asks which area suits families or a religion
No steering; it offers listings by stated criteria such as price and rooms, or a person.
Question not covered
It says it does not know and offers a person; the question goes on the review list.
AI provider outage
The widget falls back to a contact form and the phone line to voicemail.

Architecture

An AI assistant for an agency at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Enquirer Web, WhatsApp, call Assistant service n8n or Laravel Language model Claude, Gemini, GPT Listings and FAQs Feed and approved Booking Viewing, valuation Negotiator Advice, complaints Transcripts Weekly review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 An enquirer asks a question and is told they are talking to an automated assistant.
  2. 2 The service fetches the live listing data and approved answers and passes them, with fixed rules, to the model.
  3. 3 Routine questions are answered with a link; viewings and valuations are booked or sent as requests.
  4. 4 Advice, complaints and anything unclear go to a negotiator, and every conversation is logged.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI chatbot & phone assistant for agents project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Real questions from calls, chats and portal messages; what the assistant may and may not answer.

  2. 02

    Answer library

    About 1 week

    Approved answers, hand-off wording and the listing data fields to use.

  3. 03

    Build

    About 2 weeks

    Chat widget, WhatsApp or voice line, listing retrieval, booking, hand-off and admin view.

  4. 04

    Test

    1 to 2 weeks

    Real, tricky and fair housing test prompts; the agency signs off before launch.

  5. 05

    Launch

    2 to 3 days

    Soft launch out of hours or on lettings first, then widen.

  6. 06

    Support

    Ongoing

    Weekly transcript review at first, then monthly answer updates.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models n8n AI Agent node or Laravel Your CRM or listing feed Website chat widget Twilio voice or WhatsApp Google or Microsoft calendars

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and answer library

    Real questions collected, answers written and approved.

    $500 – $1,200

  • Build

    Assistant service, chat, WhatsApp or voice, retrieval and admin view.

    $1,200 – $4,000

  • Integrations

    Listing feed or CRM, calendars and alerts.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and fair housing prompts tested before launch.

    $300 – $900

  • Launch and training

    Soft launch, transcript review and team walkthrough.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. A phone line costs more to build and run than website chat. Model usage, WhatsApp and telephony are billed to your accounts directly.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model usage: Billed by the provider per use; chat volumes for a single agency are usually a modest monthly amount.
  • Messaging or voice: Twilio or WhatsApp at the provider's published rates; a voice line costs more to run than chat.
  • Hosting: n8n Cloud from about €20 a month, or your own server.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: tell people they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them they are interacting with an AI system, from 2 August 2026. We add the disclosure everywhere.

Source: artificialintelligenceact.eu

US: no steering or discriminatory statements

HUD treats discriminatory housing advertising and statements as illegal under the Fair Housing Act, including on digital platforms, so the assistant is tested against steering prompts.

Source: www.hud.gov

US: automated calls and texts

Calls and texts using an artificial or prerecorded voice, and marketing texts, are covered by the TCPA rules, so outbound use needs the right consent.

Source: www.law.cornell.edu

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

AI chatbot for real estate questions questions, answered.

Listing facts from your feed, your fees and process, viewing availability and opening hours, all from data and wording you approved. It does not give advice on price, mortgages or contracts.

Yes, from approved slots, or it creates a request for the branch to confirm. We usually start with requests and move to direct booking once the team trusts it.

It never asks about or responds to protected characteristics, answers every enquirer the same way and is tested with steering and discrimination prompts before launch. A person reviews transcripts weekly at first.

Yes. It says so at the start and offers a person at any time. In the EU that is required under the AI Act from 2 August 2026.

For out-of-hours calls and simple questions it can be. Voice costs more than chat, so we often start with website and WhatsApp chat and add a phone line if call volume justifies it.

Measure conversations resolved without hand-off, viewings and valuations booked, and the questions it could not answer. We set up logging from day one.

Free 20-minute call

Want this for your estate & letting agent?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call