How to build a Real Estate Agent AI Chatbot

11 Sep. 2019 - - Total Reads 3,354

We’ve just gone through the learning curve of building (and rebuilding a number of times) a hopeful “Turing Test” passable Real Estate Agent AI Chatbot. Was it easy? Hell no. The Turing test is a huge benchmark for a reason– the natural language we bumble through even as a toddler, is incredibly sophisticated. To get a computer to do that like a real Real Estate agent in a SciFi show (there may not be too many real estate agents in a sci-fi show, but you get the idea), is really light years ahead.

It’s live and working. Check it out on MotionProperty.com.au and their Facebook page (yes, it answers all live chats on Facebook as well). We have at best 6 months of programming to improve it.

How to build and AI Chatbot

The AI Part of any chatbot engine is really just a comparison tool. It looks for like-minded words or phrases, and comprehends if you replace one for another. For example, “Rent” could be “Lease” or “Renting”, and as soon as you give that example, is Rent as in “lease my place” or “I want a place to rent”, interchangeable again is “I want to live there”, which also means “live” as in performance. This shows how fast things can escalate outside the scope of AI or at best, form part of the training inside the AI platform.

We came up with a couple of processes to support these challenges– you can approach this from Top-down or Bottom-up.

Bottom-up is where you sort of go for it, and start with an open-ended “ask-me-anything” chat and try building in intended cornerstones to get to the bottom- the info you want to capture, the person’s name, location of interest, budget, etc.

Top-down is where you build out an elaborate data flow diagram (DFD pictured here), showing all the “pathways” you think how most conversations will go down. We did this from our second rebuild onwards for two reasons:

First, there were too many options to cover off in the Bottom-up approach. So while we did get something working, the potential conversation pathways were enormous, and conversations that got to the end were under a few percent.

Second, we could launch what was basically a multi-choice questionnaire from the DFD, so that 100% of the conversations reach a conclusion. It wasn’t anything better than a dumb form at this point, but it gave us a lightbulb moment. We could tackle the programming in a piecewise process, removing layer by layer of the multi-choice into smaller AI conversations. This approach worked superbly. As we pulled out the first multi-choice from the top of the DFD tree, it changed the entire feel of the conversation– far more human and realistic.

While Bottom-up chatbot programming can work, it seems only applicable when programming something simple, such as handling a single Question pathway (example below). This liner pathway is essentially a zoomed-in version of every box in the larger DFD.

For our “Be the Agent” AI chatbot with 5-6 key services and a range of sub-trees for every conversation point, the Top-Down approach has been a great solution so far, and is only getting better with every iteration.

For more info on our Chatbot strategy, design and development services, please see our section on Chatbots under Our Services.

Michael Simonetti
Posted by:

Post Reads: 3.4K

Share this

Go on, see if you can challenge us on "How to build a Real Estate Agent AI Chatbot" - Part of our 168 services at AndMine. We are quick to respond but if you want to go direct, test us during office hours.

Add Your Comment

Trusted by

Aqium Gel
High Street Armadale
Crumpler
MyAccount
Engine Swim
National Museum of Australia
Chia
Ello
Plan It Sync It
Macmillan Publishing
The Royal Melbourne Hospital
Passage To India
Grow Your Business
The Burger Cheese
Castran Gilbert
Federation Square
Associated Press
Arthur Galan
Atlantic Group of Companies
Positive Poster
MAP
Palace Cinemas
Bank of Cyprus
Ego Pharmaceuticals
Celebrate Health
Vitura Health
Inferflora
Toni&Guy
Unsw Australia
21st Century Australia Party
Instant RockStar
HGG 
Victorian Government
Plants
Engineers Without Borders
SunSense Digital Agency
LBG Australia and New Zealand
131 Pizza
Garmin
Think & Grow Rich Inc
SMH – The Sydney Morning Herald
Macpherson Kelley
Peter Mac
Max’s
Ubertas Group
OMS – Order Management System
Federation University Australia
Natralus Australia
Loan Market
Craft CMS
Parker Lane
Tribe
National Relay Services
Movember
Heat Holders
Australian Organic Food CO
iPrimus
Ebay
Mecca Brands
Acquia Certified Site Builder Drupal
POSTER Magazine
Maxine
DeeWhy Market
Magento Solution Specialist
Xavier
Rydges
DepSkin.com
Tomorrow Stars Basketball
DUSA, Deakin University Student Association
Street Kitchen
GooglePlay
Passage Foods
Matchbox Homewares
Brisbane Times
One Shift
AC/DC
Dinosaur Designs
CAN- Common Wealth Bank
Tassal
ISO Certified
Banki Haddock Fiora
Naturtint
James Buyer Advocates
King Wood Mallesons
Fresh Cheese Company
Bostik
Grays Ecommerce
Boston Consulting Group
Sunday Creek
Cleanfit
Metricon
Beaumont
Sports Power
PranaOn
Madman Entertainment
Buy Aussie Now
Green St Juice CO
Oracle
Australian Physiotherapy Association
Thomson Geer
Van Egmond Group
Cooper Mills
Kadac
Jetstar
Amino Active
Uber
Tek Ocean
Cell Therapies
Toy World
Viktoria & Woods
Melbourne Central
Telstra
Carlton Football Club
Microsoft Certified Azure Fundamentals
OJAY
Coles
Elucent
Herbert Smith Freehills
The Age
Vendor Advocacy Australia
Jalna
Eway
Catholic Insurance
NMI Insurance
Schiavello
Appstore
Melrose MCT
Arc One
Drupal
Bulk Nutrients
Watches of Switzerland
NGS Super
Kay&Burton
Marshall White
Melbourne Heart
SwinBurne University of Technology
McArthur Skincare
Forbes
QV Skincare
Hanover
Grainshaker
TPP
Australian Anthill
BlackMores
Bondi Sands
The University Of Melbourne
Liveoneday
Wild Rhino Shoes
Moov Head Lice
Windsorsmith
Melrose Health
Australian Government
Etihad Stadium
Hairhouse Warehouse
Google
Dial Before You Dig
ABC
VISSF
Adobe Professional
Royal Freemasons
French Tables
Focus On Furniture
Fairfax Media
Florsheim Shoes
Gadens
Fast.co
News
Gilbert+Tobin
Melbourne Sports and Aquatic Centre – MSAC
Fit My Car
White Suede
Shell
Bigcommerce
Smart Company
GPT Group
NextTech
RMIT University
Mark Alexander Design
Magento
Bintani Australia
Cronos Australia
Rackspace
The Canberra Times
Paypal
WTFN
Scrum.org
ACTUATE IP
Switzer Media+Publishing
The Fortune Institute
CSquared Executive
Rock Pool Group
Taylor Rose
ISO CERTIFIED 27001
CB Richard Ellis
Oakdale Meat Co
Novvi
Mamma Lucia
ADP Payroll

Testimonials

AndMine's Marketing Software ensures we stay on-brand no matter who in our office creates the campaign. We love that AndMine take all the IT complexity out of our online marketing so we can focus on results Emma Gleeson, QV Skincare

More Testimonials
AndMine-Google-Partner-Signature