Beginners Guide to Chatbots, Virtual Assistants & their differences
People still ask me if chatbots are mere click-bots. You know, the ones where you hope to chat but are presented with buttons? The ones that give chatbots and virtual assistants a bad name. The ones that chatbots are - not?
What is a click-bot?
A click-bot is just an interactive way to engage users or answer their queries; which a website is already undertaking. It doesn’t take user inputs and has a rigid flow. Some conversational AI platform vendors merely claim to have a conversational interface, yet all the user is doing after the initial request is clicking on predefined options. Although this may suffice for certain use-cases, it is not scalable to others. In fact, this isn’t a virtual assistant at all. What's more, such implementations do not make up a conversational AI platform.
The value proposition of a chatbot is that it’s supposed to provide a delightful customer experience. An experience to ‘remember’. For businesses, it’s supposed to save a lot of time, money, and resources.
If a click-bot doesn’t account for all user queries other than those it has been designed for, which is limited and pre-defined, how can that be a delightful experience to remember? Moreover, queries unanswered will be taken up by human resources in the company so how does it save time or money? Well, it doesn’t. But take a moment to think back on a time where a chatbot helped you or added zest with a little humor to the conversation?
Can’t think of any? Because there weren’t any.
But more on that in a bit. First, let’s discuss chatbots.
What is a chatbot?
As per Wikipedia - A chatbot is a software application used to conduct an online chat conversation via text or text-to-speech, in lieu of providing direct contact with a live human agent. Designed to convincingly simulate the way a human would behave as a conversational partner, chatbot systems typically require continuous tuning and testing, and many in production remain unable to adequately converse or pass the industry standard Turing test.
The term "ChatterBot" was originally coined by Michael Mauldin (creator of the first Verbot) in 1994 to describe these conversational programs.
In simple terms and on a fundamental level, a chatbot is a software program that interacts with a user via an interface to service repetitive tasks such as FAQ-answering, showcasing services/products, etc. A chatbot can be deployed on any platform ranging from a website to messaging applications like Facebook Messenger, Viber, WhatsApp, etc. The difference between a website and a chatbot is that a website is an interface with information spread across pages while a chatbot is a program running on an interface to provide the user with the information it needs. With a chatbot, one can streamline the information and fast-pace any transaction/query since the information is fetched by the chatbot instead of the user having to look for it.
“~90% of our time on mobile is spent on email and messaging platforms. I would love to back teams that build stuff for places where the consumers hang out!” — Niko Bonatsos, Managing Director at General Catalyst
You’re probably reading this on your smartphone besides simultaneously messaging on WhatsApp chatbot, Facebook Messenger, or WeChat. Let’s say I have an e-commerce clothing store and would love your attention on my catalog, I could -
Get a website
Get a mobile application
Run campaigns to get your attention through e-mails, advertising, etc.
The fact remains that the above channels aren’t my daily essentials and so I’m just not that interested. If my brand had a WhatsApp chatbot, you could just message me to get your order delivered - from choosing items to payments, all on one platform. From lead generation to loyalty, the transitions for a user in his journey are drastically reduced.
Raghu Ravinutala, the founder of Yellow Messenger, saw the potential and the need for enterprises to engage with customers in a more frictionless way on platforms where they really are active.
“Major shifts on large platforms should be seen as an opportunity for distribution. That said, we need to be careful not to judge the very early prototypes too harshly as the platforms are far from complete. I believe Facebook’s recent launch is the beginning of a new application platform for micro application experiences. The fundamental idea is that customers will interact with just enough UI, whether conversational and/or widgets, to be delighted by a service/brand with immediate access to a rich profile and without the complexities of installing a native app, all fueled by mature advertising products. It’s potentially a massive opportunity.” — Aaron Batalion, Partner at Lightspeed Venture Partners
What is an intelligent virtual assistant?
As discussed, chatbots have a limited learning loop. It can only handle queries that are already fed to it manually. This can work in some cases but isn’t a viable solution in the long run.
Intelligent virtual assistants (IVAs), sometimes referred to as AI conversational agents, process human inputs to deliver accurate responses, predictions, and decisions. They are powered by a combination of the conversational user interface (CUI), NLP, and semantic and deep learning techniques (such as DNNs, natural language processing, prediction models, decision support, and personalization). They may also be called Advanced virtual assistants which is perhaps the next level of maturity in virtual assistants.
IVA’s and AVAs assist people and automate tasks. AVAs are deployed in several use cases for different user types, including virtual personal assistants, virtual customer assistants, virtual employee assistants, and others.
What this means is that virtual assistants have a heuristic model and are programmed in a way that their defined models predict user intent to provide not only accurate but proactive responses. Deep-learning models are nothing but patterns that facilitate a virtual assistant’s functioning and learning. An intelligent virtual assistant is trained on a vast set of dynamic, unstructured data and with deep-learning and deep neural networks, this data is structured and used for decision making.
Yellow Messenger’s unique NLP engine powers virtual assistants that are based on zero-shot learning models - accurate results with little or no data for training. This means you can get a plug and play intelligent virtual assistant, in no time!
With Yellow Messenger’s intelligent virtual assistants when a virtual assistant is presented with a query that it has not accounted for, it can still bring out a response for the user with our fallback feature.
Key differences between the chatbot and intelligent virtual assistant
So if you haven’t got that delightful experience from chatbots, it’s because chatbots are a new type of User Interface, and designing conversational UIs is a new paradigm.
Yellow Messenger is one of the very few today that builds intelligent virtual assistants that truly provide a worthwhile experience both for employees and customers. Gartner has recognized Yellow Messenger is the leading conversational AI platform as well as a key vendor in CX automation and intelligent virtual assistant provider. Yellow Messenger is a global leader in WhatsApp chatbot implementation for enterprises.
Talk is cheap. Looking for a chatbot or a virtual assistant? You’ve come to the right place. Request Demo
Aavi Mathuan is a marketer, web dev and content creator at Yellow Messenger. Her core interests lie in the space of technology and brand psychology. Her natural affinity towards design, content and storytelling is refreshingly perceptive and insightful. She lives with her happy puppy in Bangalore, India.