Join us for a live demo of the Operations Center on December 6th at 11:00 AM ET  – Register Here


The 6 Steps to Designing a Great Virtual Agent

Share this 

Share on facebook
Share on twitter
Share on linkedin

There has been a massive increase in the use of enterprise virtual agents in the past few years. Unfortunately, many of these are weak and underperforming generally due to a lack of good planning.

At Wysdom, we have designed and launched dozens of the best virtual agents in the world and have developed a real-world design methodology that delivers the best results every time.

By using a tried and tested methodology every detail of a virtual agent can be planned in advance, resulting in the best performance and customer experience possible.

These are the 6 steps that your team should consider when designing a virtual agent customers will love. We call the output a virtual agent “blueprint”.

1. Topics

Virtual agent design begins with an understanding of all of the topics that will be covered by the virtual agent. Using historical data and machine learning technology, you will identify hundreds of topics that the virtual agent is expected to handle.

Whether the virtual agent will engage in a conversation and try to resolve an issue or hand off directly to a live agent, it will need to accurately identify the topic. Every topic will be rated for its ability to generate revenue, save money or impact customer satisfaction.

During this stage the virtual agent design team will:

  • Determine which topics customers contact you most about
  • Validate which topics should be handled by virtual and/or human agents
  • Prioritize virtual agent topic training based on business objective and feasibility
  • Create a phased topic roadmap based ROI per topic

2. Channels

Channels are where your customers connect with your virtual agent. Choosing the right channels and understanding their capabilities is a key part of design.  

Text and voice will both be investigated here and a plan will be put in place. Generally, starting with text-based channels (Webchat, Facebook Messenger, Apple Business Chat, SMS, WhatsApp, etc.) are best suited for the early stage of your virtual agent program, and voice is typically included at a more mature stage. 

In this stage the team will:

  • Identify which channels customers currently use and prefer
  • Consider the capabilities and limitations of each channel and align this information with topic priorities from the work above
  • Consider the journey and timing to migrate from text channels to voice channels
  • Create a phased channel roadmap based on ROI per channel

3. Architecture

There are a lot of moving parts surrounding your virtual agent platform. Getting the right technology is critical to the long-term success of your virtual agent program. Choosing the virtual agent platform that meets your requirements and then considering integration to back-office systems, long-term conversation data storage, security, compliance, and performance should all be taken into account when designing your virtual agent architecture.

During this step, the virtual agent design team will create an architecture that will scale and address all of your customer needs including:

  • Select the best virtual agent platform and components to support your requirements 
  • Consider integrations to back-office systems, conversational data storage, and third-party tools
  • Prioritize integrations by evaluating customer value and implementation complexity
  • Deliver a phased architecture plan

4. User Experience

UX covers everything about how your customer will experience your virtual agent. This might include what personality it will have, how many languages it will speak, will it combine voice and text channels, what journeys will be configured, how will hand-off to a live agent take place, and more.

The virtual agent design team defines placement, behaviour, and other best design practices that will ensure exceptional customer experiences by:

  • Leveraging Wysdom’s Conversational AI user experience best practices guide
  • Plan chat client design, placement, customization, and trigger behaviours
  • Formalize virtual agent persona, branding tone, and manner

5. Team

It takes an experienced team to design, build, and operate a great virtual agent. This isn’t something that will be handled by one person or two part-time employees. The best virtual agents in the enterprise have sizeable teams behind them continuously improving and adding capabilities to the virtual agent program.

Wysdom has created virtual agent teams for dozens of organizations and has a structure that delivers results. There are 10 key positions that require unique skills. Recruiting, onboarding, and developing a great team will pay dividends in virtual agent performance.

During this phase the team will:

  • Review what skills exist within your organization, which are needed, and what model to use (outsource, build in-house, hybrid, etc.)
  • Identify part-time specializations required to be successful
  • Design a team for multiple phases of the virtual agent program
  • Cost out options for use business case evaluation

6. Business case

A virtual agent is a significant investment for any organization and determining the return on that investment is key as you venture into this new space and align objectives across departments.  All of the steps above are going to provide the costs and benefits you can expect from your well-designed virtual agent program.  

Pulling all of the pieces together into a business case is critical before you train the first utterance into your virtual agent platform.

The final step in creating your virtual agent blueprint is adding up the numbers and finalizing the business case:

  • Review virtual agent architectural components to understand all associated costs
  • Review expected KPI’s to assess impact to revenue, costs, and customer experience
  • Ensure you have ROI goals for each stage of the program roadmap

After these 6 steps have been completed, you will have a comprehensive virtual agent blueprint. This process has been used to build hundreds of successful virtual agents, and the tools have been honed to deliver fast and effective plans. 

If you want to add some Wysdom to your virtual agent program planning process, let’s get started.

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.