How to build a Real Estate Agent AI Chatbot

11 Sep. 2019 - - Total Reads 2,335

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: 2.3K

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

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

Testimonials

Not only is Michael professional but he is also a great friend to have in your court. He is balanced in his advice, fair in his quotes and has the best twitter feed for all things tech - i highly recommend you follow him and also hire him! Clare Smith, GM – Brand & Marketing Communications at Sensis

More Testimonials
AndMine-Google-Partner-Signature