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:

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.

CHATBOT PLATFORMS. How to choose the right one?

Chatbot platforms are essential tools if you need to build and run a chatbot.
There are many available on the market, big and small, popular and not so much.

Here are some useful thoughts that should help you navigate the complex world of chatbots and conversational AI solutions.

All chatbot platforms can be split into two categories: those that let you create chatbots without any programming, and those that require programming. Now, the idea that you don’t need to possess technical knowledge to build a chatbot seems appealing but the reality is not so rosy. In fact, I have yet to see a professional chatbot created without coding.
Chatbots rely on sophisticated algorithms and advanced knowledge of linguistics. These technologies are so complex that at the moment there are no plug-and-play solutions available. The companies like Chatfuel, Manychat, Flow XO and many others are attempting to fill that void and offer chatbot platforms that are simple in use. The best way to make the chatbot creation simpler is by dropping the need to code them. However this simplicity comes at a price: chatbots made without coding are limited, rigid and in general, primitive.
So to summarize: if you want to impress your girlfriend use Chatfuel. If you need a professional chatbot that delivers on your business goals and provides customer satisfaction use advanced chatbot platforms with programming capabilities.

One of the main, if not the main, tasks of the chatbot platforms is to connect your chatbot to the user interfaces. There are many ways for your chatbot to interface with the world: on Facebook messenger, on the website, on the mobile app, via SMS, on Twitter , on Skype, on Slack, on Telegram, and more. A good chatbot platform should seamlessly connect the chatbot to most of these channels. Chatbot platforms do not make your chatbot smarter. For this you need AI Engines (brief disucssion on AI Engines: http://nmodes.com/entry/2018/03/29/what-are-ai-engines-and-how-choose-one/).

For best results create your chatbot on a chatbot platform, then connect it to AI engine.

One of the top chatbot platforms on the market is Microsoft Bot Framework. It is robust, powerful, with a wide variety of useful functionality built-in. Another good chatbot platform is DialogFlow. DialogFlow has a slightly different architecture in the sense that it is a chatbot platform and an AI Engine all in one interface.

Chatbot platforms can be used to create conversation flow for your chatbot. There are several schools of thought here: some prefer to delegate conversation flow to AI engines. Chatfuel and other tools with the emphasis on simplicity (build your chatbot in minutes, no coding necessary) offer easy graphical interfaces for conversation flow creation. And there is always a reliable option to create conversation flow in an old-fashioned way, programmatically.

Which option to choose? Depends on your chatbot requirements and the business needs the chatbot is expected to address.And if you have questions feel free to ask: http://http://nmodes.com/contact-us/