5 Steps To Training Your New Bot

Share this 

Share on facebook
Share on twitter
Share on linkedin

So you’re thinking of implementing a Bot like every other company on the planet but there is this issue about training the damned thing. There has been an endless stream of coverage about all of the wonderful things Bots are going to do for business by automating conversations with customers.  The problem is, Bots are only as good as the training that goes into them and training isn’t something you just knock off in a few days.

Many Bot startups seem to want to treat Bots like an IVR, choose the top 20 use cases and train your Bot around those needs.  Considering the IVR is probably the most hated piece of technology invented in the last 50 years, replicating that process is probably a horrible idea.

Very few, if any, Bot vendors have actually operated these things out in the wild with millions of customer interactions over a number of years so it makes sense that we’re not yet hearing about the best practices when it comes to training a Bot.  The reality of training a Bot is a little more complex than might be obvious at first glance.

At the highest level you need to consider all of the various channels that customers are using to contact you (Messenger, Twitter, Kik, WeChat, Web Chat, Mobile apps, Alexa, etc…), the unique UI capabilities of each channel and multiple languages to be supported.  You definitely don’t want to train in multiple systems.

This is probably a little more complex than just plugging in the top 20 use cases, let’s look at the best way to train a Bot to deliver real value to your enterprise and customers.

Step 1: Pre-training your Bot.

This is what many Bot companies are pitching as the whole training program, when it is really only the first step of a real training plan.  This is where you go to your customer care or tech support department and see what they think are the top reasons your customers are contacting your company.

By sampling the chat logs, call recordings and digging through the typical support material that the reps use you will get closer to understanding the customer intent.  This is a decent place to get started on training your Bot.

Step 2: Analysis of all customer interactions.

Every day your customers are telling you what they want to know and what they really care about.  Many Bot companies are assuming that you will know what your customers want and if you don’t that it is your problem to figure it out.

A tool that analyzes customer questions in real time is a key piece of any Bot solution. The analysis will tell you what your customers actually want to do with your Bot and will let you focus your training efforts where it pays the biggest dividends; this is probably the most important part of any Bot training framework.

Step 3: Train the Bot.

With all of the rich information coming from the analytics where to train is obvious. A good Bot solution will now let you train in one location and take into consideration each channel’s capabilities and limitations. What you present in FB Messenger won’t work in a pure text Bot, and what you can present in Twitter may not work in your web chat UI.

A well-architected system will let you train for both conversational and Q&A type of channels in one system.  Multiple languages should be automatically generated or updated if you have created a new scenario or just updated an existing one.  Training multiple Bots to solve this problem is insanity as described in this previous VentureBeat article.

Step 4: Measure the effectiveness.

Use every question from every customer from every channel every day to determine how effective your Bot is. There are many ways to measure the level of satisfaction of your customers during their interaction with the Bot.  Over time you will determine normal thresholds for each parameter and then can use anything outside the norm as an indicator of failure.

Your false positive rate should be monitored closely here.  Delivering the wrong answer is far worse than not delivering an answer at all so this is critical to measure.  If you are delivering the wrong answers more than 3% of the time your system should be taken back to the drawing board.

Step 5: Continuously improve.

Training your Bot will never be finished.  Even if you have a simple Pizza ordering Bot you’re going to have to continuously learn new language from your customers about how they want to order, add new channel support and new products.  If you have a more complex business and are using your Bot for customer service then you should plan to invest a considerable effort in ongoing training.

Don’t get caught up in the Bot hype and deploy something that is going to create more work in the longer term.  A fully thought out Digital Care strategy will provide large customer satisfaction and economic benefits.

We use cookies to ensure that we give you the best experience on our website. By clicking “I Accept” or if you continue to this site, we will assume that you consent to the use of cookies unless you have disabled them.

Data Scientist

As a Data Scientist, your day-to-day will involve writing queries, building dashboards, and preparing analytical reports about product performance for our clients and the Wysdom.AI team.  You will work with SQL, Tableau, and Python and ML Frameworks/libraries (among other tools) to create stunning visuals showing how Wysdom.AI is making their customers’ experience even better.

Implementation Engineer

As an Implementation Engineer you will be responsible for the solution integration of an enterprise grade conversational AI experience from a technical perspective. You will work closely with the lead solutions architect and be the technical face of the implementation team and lead the customer through the entire implementation cycle. You will work with one of the most diverse teams of linguists, data scientists, and innovators to deliver the best AI enabled customer experience.

Solution Architect

As a Solutions Architect within the Client Services team, you act as trusted advisor, responsible for the technical requirements and end to end solutions integration of Wysdom cognitive services within the client’s environment.  You will work with one of the most diverse teams of linguists, data scientists, and innovators to deliver the best AI enabled customer experience.

Cognitive Data Specialist

As a Cognitive Data Specialist, you will be responsible for the performance of the AI and quality of the corpus and will focus primarily on the VA training.  You will work with the client as required to ensure corpus is performing in an optimal manner.

Conversational Experience Designer

As a Conversational Experience Designer, you will be responsible for the designs of the overall customer experience, including the end-to-end dialog flows & journeys of the solution ensuring  design leverages  UxD best practices for optimal customer experience.

Conversational AI Specialist

As a Conversational AI Optimization Specialist, your responsibility will be to help drive the success of our solution for our clients. This involves building conversation flows, performing AI training, and partnering with clients to enhance their deployments.

Conversational AI Lead

As a Conversational AI Lead, you will be responsible for leading all Conversational AI program activities.  You will work with all team members to ensure deliverables are completed on time, with high quality and exceeds client expectations and goals.

Program Director

Responsible for the overall success for the client, including the end-to-end delivery and optimization of the solution, you will manage the sales process from pillar to post, including technical and commercial proposals, pipeline management, sales forecasting, and contractual documentation.

David Trotter, Wysdom

David Trotter

SVP, Sales & Marketing

David has 30 years of global sales leadership experience as a collaborative leader who believes in a strong team concept within sales and marketing organizations. David has spent many years working with growth companies and enjoys being face to face with customers and partners to create solutions that have a lasting effect on the customer’s business environment. 

Prior to joining Wysdom, David was the Vice President, Sales at Scalepad, and previously spent 11 years as Vice President for Latin America and Asia Pacific for Absolute Software. He also held senior sales management positions at GE Capital and Clevest.  

Michel Benitah

VP, Optimization & Delivery

Michel has 20 years of experience in leading the successful delivery of Conversational AI and Natural Language Customer Care solutions to some of the largest financial, telco, healthcare, utilities, and retail enterprises throughout North America. 


Prior to joining Wysdom, Michel spent 20 years at Nuance Communications, holding senior management and leadership positions within the enterprise division, most recently as director of the Toronto office and professional services team.

Frederic Lam

SVP, Sales

Fred brings in 25 years of international experience in sales and business development across North America, the Caribbean, Asia-Pacific, Europe, and the Middle-East.


Prior to Wysdom.AI, he held sales leadership positions at Oracle, Redknee, and Movius/Glenayre, successfully growing revenues in both large and small organizations. Fred has also been involved in the start-up community in the earlier stages of his career as an Investment Manager with SP Capital and was an alternate director on a few investee companies.

Karen Chan

Chief Engineering Officer, Co-Founder

With 20 years of experience in software and mobile, Karen has held senior technical roles at 5 startups, including Wysdom.AI, Clickfree, Mobile Diagnostix (HP), Teamatic, and Virtualthere.

Karthik Balakrishnan

Chief Technology Officer

Karthik has over a decade of hands-on, proven global expertise in emerging technologies and implementing intricate platforms and solutions for telecommunications and enterprise during his time at Amdocs, with senior positions in their India, Cyprus, America, and Canada offices.

Nitin Singhal

Chief Operating Officer

Nitin has over 20 years of success in global executions of business technology, driving operational efficiency and digital scalability for some of the world’s largest enterprise clients. 


Nitin spent 16 years at Redknee holding executive positions in Research and Development, Customer Operations, Partner Alliances, and most recently as COO.

Jeff Brunet​

President, Co-Founder

Jeff has more than 20 years of experience in the startup world, founding and growing 4 software companies: AracNet, Mobile Diagnostix (HP), ClickFree, and Wysdom.AI. 


His in-depth understanding of software development and the challenges in making new technologies successful in the startup world prove invaluable as he serves on the boards of XMG, SurfEasy (Opera), Locationary (Apple), Groupie, and as an advisor to Pushlife (Google), LogMeIn (IPO) and HP. 


Jeff holds 23 issued patents in the wireless and consumer electronics spaces and is the lead inventor on 30+ pending patents.

Ian Collins​

CEO, Co-Founder

Ian has founded and grown 6 technology companies over the past 20 years, primarily in the enterprise software space including Wyrex, Mobile Diagnostix (HP), Clickfree, and most recently Wysdom.AI. 


Ian invests, mentors, and sits on the boards of several startups in the Toronto area.