What Is AI Engine and Do I Need It?

sasha uritsky

Mar 29, 2018

Chatbots and assistant programs designed to support conversations with human users rely on natural language processing (NLP). This is a field of scientific research that aims at making computers understand the meaning of sentences in natural language. The algorithms developed by NLP researchers helped power first generation of virtual assistants such as Siri or Cortana. Now the same algorithms are made available to the developer community to help companies build their own specialized virtual assistants. Industry products that offer NLP capabilities based on these algorithms are often called AI engines.

The most powerful and advanced AI engines currently available on the market are (in no particular order): IBM Watson, Google DialogFlow, Microsoft LUIS, Amazon Lex.

All these engines use intents and entities as primary pnguistic identifies to convey the meaning of incoming sentences. All of them offer conversation flow capability. In other words, intents and entities help to understand what the incoming sentence is about. Once the incoming sentence is correctly identified you can use the engine to provide a reply. You can repeat these two steps a large number of times, thus creating a conversation, or dialog.

In terms of language processing ability and simplicity of user experience IBM Watson and Google DialogFlow are currently above the pack. Microsoft LUIS is okay too; still, keeping in mind that Microsoft are aggressively territorial and like when users stay within their ecosystem, it is most efficient to use LUIS together with other Microsoft products such as MS Bot Framework.

Using AI engine conversation flow to create dialogs makes building conversations a simple, almost intuitive, task, with no coding involved. On the flip side, using AI engine conversation flow limits your natural tendency to make conversations natural. The alternative, delegating the conversation flow to the business layer of your chatbot, adds richness and flexibility to your dialog but makes the process more comppcated as it now requires coding. Cannot sell a cow and drink the milk at the same time, can you?

Amazon Lex lacks the semantic sophistication of their competitors. One can say (somewhat metaphorically) that IBM Watson was created by linguists and computer scientists while Amazon Lex was created by sales people. As a product it is well packaged and initially looks pleasing on the eye, but once you start digging deeper you notice the limitations. Also, Amazon traditionally excelled in voice recognition component (Amazon Alexa) and not necessarily in actual language processing.

The space of conversational AI is fluid and changes happen rapidly. The existing products are evolving continuously and a new generation of AI engines is in the process of being developed.

Interested in reading more? Check out our other blogs:

WHY ALL CONVERSATIONAL AI SOLUTIONS ARE CURRENTLY CUSTOM MADE

All quality conversational AI solutions such as chatbots, voice bots, virtual assistants are customized. The reason is because conversational AI solutions have a component called AI training that has to be individually tailored to the needs of each business. Currently AI industry does not have a suitable solution to automate this component.

There are, of course, easy-to-use, scalable products such as Chatfuel, ManyChat and others, but they do not provide sufficient quality and therefore do not add value to the professional sales or customer service process.

The next generation of conversational AI solutions will be scalable, while capable of delivering the level of quality required by businesses and professional organizations. nmodes is among a limited number of AI companies, with sufficient level of technological knowledge and deep enough understanding of underlying linguistic processes. working on delivering this kind of solution to the market as quickly as possible. In the meantime, customizable AI solutions, with personalized AI training component, is industry's best option.

Building 24x7x365 Customer Support and Online Sales... FOR FREE (Almost)

We’ve all seen the numbers and they tell us that customers are more likely to make a purchase if they’re able to speak to a representative at the time of purchase. Study after study shows that if you can prevent even the smallest percentage of customer defection revenues and profitability can literally skyrocket as much as 80%. Just as important, the faster is your service the better is customer experience.

The same can be said for customer support. More than 70% of customers say that responsive customer support providing fast, courteous, relevant and contextual answers to their inquiries are the most important factors in determining the quality of customer service and the likelihood of that customer doing business with the company in the future.

As our world becomes even more “on-demand” and global, providing around the clock sales and customer support is quickly becoming a key differentiator. Customer’s desire to do business with companies on their own schedule and terms are driving financial growth and customer loyalty across all sectors and industries. Companies that neglect this “always on” requirement not only lose out, but need to find ways to be competitive.

Unfortunately, only the largest companies have the financial resources to deliver 24x7 customer support and sales operations. Still many of the largest companies can’t justify the expense of building out and staffing a 24 hour contact center. While outsourcing to a BPO is always an option, statistics show a diminishing return for outsource customer and sales support operations.

As customers continue to drive up the use of chat and social communications for customer support and sales, along with the incredible growth in Artificial Intelligence technology, smart companies on the forefront of customer service now have the ability to offer around the clock service for a large portion of their customers.

Think about this: While the average phone support call has previously been measured at almost 6 minutes, the average chat session lasts just 42 seconds, indicating that the vast majority of customer support issues are simple and only require limited information in order to leave a customer informed and satisfied with the interaction.

Today Artificial Intelligence can deliver a personalized, informed, and contextually relevant response to just about any question related to most customer inquiries. Add on the fact that AI actually “learns” as it interacts with people and information and the value to the customer and the vendor actually increases over time. Wouldn’t we all like to have immediate service with zero wait times and fast, courteous response that immediately addresses our needs? I know I would.

Implementing Artificial Intelligence for customer service comes down to an application cost that, when amortized over the number of chat or social sessions it can handle, reduces customer support costs to as little as 10% of traditional contact center and agent expenses.

The one objection to relying on Artificial Intelligence in the contact center is the customer experience. There’s enough bad press out there about Chatbots and broken, robotic responses that are sometimes irrelevant that some customer support professionals are wary of any form or automation. My response to that is, while those were valid concerns; just take a look at Siri today vs. 2 years ago. The quality of responses has dramatically improved, as has the customer perception and usefulness.

What are your thoughts about Artificial Intelligence in the contact center? We’d love to hear from you.