How to build a Real Estate Agent AI Chatbot

11 Sep. 2019 - - Total Reads 2,849

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: 2.8K

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

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

Testimonials

I work with AndMine for my web development and website content management. Changes are always made quickly and I'm kept in the loop at all times - the website continues to generate awesome results. Jason Digby, Eatmusik

More Testimonials
AndMine-Google-Partner-Signature