CHATBOT PLATFORMS. How to choose the right one?

sasha uritsky

Apr 25, 2018

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/

Interested in reading more? Check out our other blogs:

Towards smarter data - accuracy and precision

There is a huge amount of information out there. And it is growing. To make it efficient and increase our competitive advantage we need to evolve and start using information in a smart way, by concentrating on data that drives business value because it is accurate, actionable, and agile. Accuracy is an important measure that determines the quality of data processing solutions.

How accuracy is calculated?

It is easy to do with structured data, because the requirements are formalizable. It is less obvious with unstructured data, e.g. a stream of social feeds, or any data set that involves natural language. Indeed, the sentences of natural language are subject to multiple interpretations, and therefore allow a degree of subjectivity. For example, should a sentence ‘I haven’t been on a sea cruise for a long time’ be qualified for a data set of people interested in going on a cruise? Both answers, yes and no, seem valid.

In these cases an argument was put forward endorsing a consensus approach which polls data providers is the best way to judge data accuracy. This approach essentially claims that attributes with the highest consensus across data providers is the most accurate.

At nmodes we deal with unstructured data all the time because we process natural language messages, primarily from social networks. We do not favor this simplistic approach, as it is considered biased, inviting people to make assumptions based on what they already believe to be true, and making no distinction between precision and accuracy. Obviously the difference is that precision measures what you got right, and accuracy measures both what you got right and what you got wrong. Accuracy is a more inclusive and therefore more valuable characteristic.

Our approach is

a) to validate data against third party independent sources (typically of academic origin) that contain trusted sets and reliable demography. Validating nmodes data against third party sources allows us to verify that our data achieves the greatest possible balance of scale and accuracy.

b) to enrich upon the existing test sets by purposefully including examples ambiguous in meaning and intent, and providing additional levels of categorization to cover these examples.

Accuracy is becoming important when businesses move from rudimentary data use, typical of the first Big Data years, to a more measured and careful approach of today. Understanding how it is calculated and the value it brings helps in achieving long-term sustainability and success.

WHAT IS AI TRAINING

AI training is a critical part of conversational AI solutions, a part that makes AI software different from any kind of software previously created.
AI training is not coding.
Unlike all other existing software which is fully coded.

Let us consider a simple example:
We create chatbots for two companies, one company is selling shoes, another is selling cars. From the software standpoint it is one chatbot solution running as an online service accessed remotely or a program available locally. In both cases they are two identical instances of the same software (one instance for the shoes company, another for the cars company).
Yet, for the first company the chatbot is supposed to talk about flip-flops, summer shoes, high heels and so on. For the second company, however, the chatbot is not expected to know any of that. Instead, the chatbot should be able to support conversations about car brands, car models, should know how to tell Toyota Camry from Toyota Corolla, etc. This shoes and cars knowledge is not programmable. It is trainable. It is not coded, instead it is a part of language processing capability that AI solutions like chatbots have. And herein lies the major differentiation and advantage of the AI solutions compared to traditional software.

How to train AI?
There are several ways to do it. Sometimes AI system can train itself, improve its linguistic ability over time. It also can be trained by professional linguists. And in some cases, by the users. The latter is the desirable scenario because businesses know better than anybody else what they want their chatbot to talk about.
It is not easy, given the existing state of AI technology, and usually requires a high level of technical knowledge. You may have heard mentions of intents and entities in chatbot discussions. These are examples of linguistic elements AI training is currently based on.
Without proper understanding of what these linguistic elements are and how language acquisition process works in existing AI systems it is better to leave AI training to professional linguists.