How to build a Real Estate Agent AI Chatbot

11 Sep. 2019 - - Total Reads 2,676

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: 2.7K

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

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

Testimonials

I wanted to thank you and your teams for the responsiveness and quality of the work you have done for the french version of the site. We had a very good feedback on the quality of the site from our French network. Vincent Berlinet

More Testimonials
AndMine-Google-Partner-Signature