Point Break – how to ride the chatbot wave without hitting the wall
Cathal McGloin, CEO of ServisBOT discusses how industries can ride chatbot innovation wave.
"Chatbot deployments continue to grow as businesses realize their value for creating seamless user experiences and improving business results. While plenty of chatbot success stories are being reported, there is a breakpoint phenomenon that is coming to light.
When training a chatbot an ‘utterance’ is anything that a user asks. A chatbot ‘intent’ is the user’s reason for their question. For example, if a user asks, “What will it cost to add my 20 year old son as a named driver?” The ‘utterance’ is the whole sentence, while the ‘intent’ is to discover the cost of various insurance policies. When training a chatbot, ‘intents’ are given a name such as ‘ListPremiums’, ‘ShowPrices’, ‘ShowDiscounts’. ‘Entities’ modify intents. For example, “Will my car insurance go up next year?” might have the intent of ‘ListPremiums’ and the entity of ‘TimeDate’, ‘PolicyType’.
As companies expand the capabilities of their bots, adding additional intents and utterances, there is a potential for the bot to reach breakpoint.
Four Stumbling Blocks for Business Chatbots
For the team at ServisBOT it was important to get to the bottom of what contributes to successful user experiences with chatbots. In doing so, we also discovered why a chatbot might work really well up to a point and then suddenly start to deteriorate or fail. We identified four underlying problems.
Too much information?
When a company architects their bot solution, the issue of intents and utterances and how many a single chatbot can handle is often overlooked.
A chatbot may work perfectly well at the outset, but as intents and utterances get added over time, this can eventually impact the user experience. Unfortunately, it’s impossible to define the exact breakpoint at which the bot performance starts to decline as it varies depending on the use case. Handling up to 100 intents and more, a single chatbot can come close to the limit that existing natural language processing (NLP) solutions can support.
Accuracy Drives Increased Intents
Another way in which a bot can be impacted is when the accuracy level needs to be raised. This may mean adding more variants of the intents. However, the increase in intents may reduce the capacity for other feature capabilities. Since language is fluid and has many nuances, aiming for accuracy can consume considerable bot capacity.
The Issue of Continuous Learning
A chatbot, once launched, cannot it be left to its own devices. It needs to be maintained as user interactions with it grow. As users interact with it new utterances may emerge that are not recognized by the bot. The bot needs to learn these missed utterances so that they can respond to them in future.
Building a chatbot is not like building an application. At any stage, a chatbot is tuned for a certain amount of data. Any changes can potentially disrupt the whole model. This a continuous task.
When a Single Bot isn’t Enough
When it comes to the different use cases that a business has for chatbots there are varying degrees of complexity. As companies become more sophisticated in their chatbot deployments, some are coming to the realization that one chatbot may not be sufficient to handle a single use case successfully.
Consider the example of a company building a chatbot to handle simple customer FAQs. Over time, they may decide to expand the bot’s capability, such as adding more personalization, managing different languages, adding small talk, handling context switching, or a combination of these. These additional capabilities can potentially erode the capacity that the bot has to deal with the original use case i.e. answering FAQs.
This breakpoint phenomenon has implications for how a business architects its chatbot solution to meet the requirements of the business use case.
Introducing a Multi-bot Architecture
An increasing number of businesses may experience the bot breakpoint in the next year. The good news is that there is a way to tackle this by adopting a multi-bot architecture with a central virtual assistant that coordinates and orchestrates multiple task-oriented bots. This approach helps overcome intent overload and subsequent deterioration of the chatbot experience.
While a single bot model works for many initial and less complex use cases, the way to think about a bot architecture is to think of bots as having different skills. Stringing together multiple bots will meet the needs of the use case without hitting the breakpoint of NLP limitations.
To address the breakpoint issue, we structure bots in a similar way to employees in an organization. Each person has a specific role and set of skills that they bring to the business. Similarly, each bot should be designed with specific tasks in mind. Just like a human, there is only so much a bot can learn, so it makes sense to train them for the skills that are specific to the business use case.
In a multi-bot architecture, individual skills can be managed using an enterprise virtual assistant, acting as a central brain that orchestrates and coordinates multiple bots that work towards fulfilling the business use case.
The virtual assistant blends independently managed bots into a unified experience, routing to the bot best skilled to respond to user requests. It also monitors the ebb and flow of conversations and enables all bots to support language detection, translation, sentiment analysis, detection of protected health information/ personally identifiable information (PHI/PII detection), and escalation to a human employee, by centralizing these skills and making them available to all individually skilled bots.
Orchestration is then critical to navigating operations across multiple bots, executing both conversational and procedural logic. This multi-bot model allows businesses to scale horizontally with thin-sliced bots by blending together FAQs, business processes, and transactions.
Breaking free of the breakpoint in 2020
Natural language processing is opening up a whole new way to engage with customers and employees. However, these users expect more from chatbots than just question and answer capabilities and want to communicate using phrases that reflect how they think and speak. This may not match the utterances designed by the organization to train their bot, resulting in a rougher user experience, or a bot that reaches its limit and fails in its original task.
Taking a multi-bot approach allows organizations to expand their chatbot horizon, delivering greater conversational and automation capabilities that deliver both a better experience for users and desired business results, without being limited by NLP.
For more information on business topics in the United States, please take a look at the latest edition of Business Chief USA.
Marketing matters: from IBM to Kyndryl
Prior to joining Kyndryl as Chief Marketing Officer, Maria had a 25-year career at IBM, most recently as the tech giant’s CMO where she oversaw all marketing professionals and activities across North America, Canada and Latin America. She has held senior global marketing positions in a variety of disciplines and business units across IBM, most notably strategic initiatives in Smarter Cities and Watson Customer Engagement, as well as leading teams in services, business analytics, and mobile and industry solutions. She is known for her work with teams to leverage data, analytics and cloud technologies to build deeper engagements with customers and partners.
With a passion for marketing, business and people, and a recognized expert in data-driven marketing and brand engagement, Maria talks to Business Chief about her new role, her leadership style and what success means to her.
You've recently moved from IBM to Kyndryl, joining as CMO. Tell us about this exciting new role?
I’m Chief Marketing Officer for Kyndryl, the independent company that will be created following the separation from IBM of its Managed Infrastructure Services business, expected to occur by the end of 2021. My role is to plan, develop, and execute Kyndryl's marketing and advertising initiatives. This includes building a company culture and brand identity on which we base our marketing and advertising strategy.
We have an amazing opportunity ahead at Kyndryl to create a company brand that will stand apart in the market by leading with our people first. Once we are an independent company, each Kyndryl employee will advance the vital systems that power human progress. Our people are devoted, restless, empathetic, and anticipatory – key qualities needed as we build on existing customer relationships and cultivate new ones. Our people are at the heart of this business and I am deeply hopeful and excited for our future.
What experiences have helped prepare you for this new opportunity?
I’ve had a very rich and diverse career history at IBM that has lasted 25+ years. I started out in sales but landed explored opportunities at IBM in different roles, business units, geographies, and functions. Marketing and business are my passions and I landed on Marketing because it allowed me to utilize both my left and right brain, bringing together art and science. In college, I was no tonly a business major, but an art major. I love marketing because I can leverage my extensive knowledge of business, while also being able to think openly and creatively.
The opportunities I was given during my time at IBM and my natural curiosity have led me to the path I’m on now and there’s no better next career step than a once-in-a-lifetime-opportunity to help launch a company. The core of my role at Kyndryl is to create a culture centered on our people and growing up in my career at IBM has allowed me to see first-hand how to prioritize people and ensure they are at the heart of progress in everything Kyndryl will do.
How would you describe your leadership style?
I believe that people aren't your greatest assets, they are your only assets. My platform and background for leadership has always been grounded in authenticity to who I am and centered on diversity and inclusion. I immigrated to the US from Chile when I was 10 years old and so I know the power and beauty that comes from leaning into what makes you different from other people, and that's what I want every person in my marketing organization to feel – the value in bringing their most authentic self to work every day. The way our employees feel when they show up for themselves authentically is how they will also show up for our customers, and strong relationships drive growth.
I think this is especially true in light of a world forever changed by the pandemic. Living through such an unprecedented time has reinforced that we are all humans. We can't lead or care for one another without empathy and I think leaders everywhere have been reminded of this.
What’s the best leadership advice you’ve received?
When I was growing up as an immigrant in North Carolina, I often wanted to be just like everyone else. But my mother always told me: Be unique, be memorable – you have an authentic view and experience of the world that no one else will ever have, so don't try to be anyone else but you.
What does success look like to you?
I think the concept of success is multi-faceted. From a career perspective, being in a job where you're respected and appreciated, and where you can see how your contributions are providing value by motivating your teams to be better – that's success! From a personal perspective, there is no greater accomplishment than investing in the next generation. I love mentoring younger professionals – they are the future. I want my legacy as a leader to include providing value in work culture, but also in leaving a personal impact on the lives of professionals who will carry the workforce forward. Finding a position in life with a job and company that offers me a chance at all of that is what success looks like to me.
What advice would you give to your younger self just starting out in the industry?
I've always been a naturally curious person and it's easy for me to over-commit to projects that pique my interest. I've learned over years of practice how to manage that, so to my younger self I’d say… prioritize the things that are most important, and then become amazing at those things.