Chatbot ecosystem: AI-powered communication
Rapidly expanding market of chatbot solutions drives many businesses to discovery of value, benefits and competitive advantages of chatbots. In this situation companies that are planning to add a chatbot to their IT infrastructure are often not familiar with the principles and components of chatbots and so decision makers are in situation that they have to define business strategies without sufficient knowledge about chatbot ecosystem. In this article we will try to clarify these aspects and describe value and impact of each component based on our experience of building chatbots.
First of all, we would like to mention that many people (even skilled and experienced in business process management) have too simplistic vision about chatbots. There are dozens of “do-it-yourself” kits on the market, but building your own solution (dedicated to needs of particular business model) without proper understanding of the whole “chatbot universe” could end with disappointment of business and customer frustration (and what is even worse – loss of trust to your chatbot). And vice versa – understanding of key business problems and implementing a few but excellent scenarios for most demanded use cases could spread a positive rumor and raise your reputation score. So, let’s take a look deeper into this topic and reveal all hidden clues that are essential for building an efficient chatbot.
Based on our experience we came to a certain vision about chatbot ecosystem. It does not pretend to be an ultimate view, but importance of each of these aspects was proven by our own solutions:
Let’s describe step-by-step all these “building blocks” and their impact on customer experience.
Communication Channels
The most obvious impact of the last decade is what we call “smartphone revolution”. This phenomenon year by year changed dramatically habits of millions of customers, and even whole new generations. So, it is essential for business to understand which communication tools are used by focus audiences and prepare respective solutions.
We find the “user persona” business analysis technique very helpful for this stage. It may reveal insights not only for chatbot implementation, but for business objectives in general.
The first step is to understand how your business interacts with customers, including existing customers as well as customers in engagement phase. The first step is to prioritize which communication channels should be supported by the chatbot. That could be a chat widget on your website, Facebook Messenger, WhatsApp, Slack, and the chat feature integrated into your own mobile app. In some cases, even e-mail or SMS could be used, if most of your customers feel comfortable with it.
Assessing overall communication volume (and analysis of trends) is essential for understanding limitations that are dictated by capabilities of each channel. For example, in SMS you can use only text of limited size, while the chat widget can potentially use any enriched content – from buttons with predefined choices to images and videos.
Conversation
Chatbot identity is one of the important aspects that have to be considered in the early stages of chatbot development. It greatly defines the emotional perception of the chatbot.
Firstly, it is essential to understand which audience is going to interact with chatbots. If you know that the focus group belongs to a particular generation, then it is worth to “equip” your bot with phrases or even slang familiar to this audience.
Another dimension to consider could be the business domain. A bot selling fashion clothes most likely will have a different “character” than a bot servicing bank customers.
However, it is not a good idea to create an illusion that a customer is interacting with a live person, because it may lead to false expectations, and at the end – frustration and distrust to the brand. Regardless of “smartness” of your bot, it is worth it to represent it as a “bot”, and not a “magician”.
Easy Come, Easy Go
After deciding on your chatbot’s character, it is worth it to focus on a set of phrases used to start a conversation and finalize interaction. These phrases are essential for impressions that the bot delivers to customers, and these impressions greatly affect satisfaction and willingness to deal with chatbots again.
Early generations of chatbots often used very simplistic or even boring phrases without variations, and this distracted many customers from trusting any chat interactions. So, if you want to avoid this “pitfall” then it is worth thinking about the variety, tone and emotions of these phrases.
Over time, with proper approach and augmentation with AI techniques your bot will surely become smarter and will be able to handle more and more diverse scenarios. But losing customer trust at the early stage of bot implementation is one of the worst scenarios.
Our recommendation is to test human perception of bot behavior on several focus groups before initial deployment. One of techniques to establish and upkeep trust to chatbots is a follow-up contact of human staff for unresolved cases.
Conversation flow
After the “greeting ceremony” it’s time to focus on the primary purpose of chatbot. Mainly the business value and the “digital brain” that provides this value. There is no common scenario for all business domains how to tailor human-bot interaction to achieve particular results. However, we will describe key components, their role and purpose to show how this “puzzle” is turned into a “picture”.
The first technique that comes into play is called Natural Language Understanding (NLU). It serves as an “interpreter” of natural human language to the data structures that can be operated by machines.
Basically, this step is used to retrieve from human input three major aspects:
- The context for understanding the environment, the area of knowledge and process where the user is trying to settle a request
- The intent is literally the intention to perform an action with an expected outcome – either settle a problem or get more information
- The entity – the object or subject of action
Now it is time for business logic to analyze and process requests and deliver proper responses to the user. On this stage a great variety of approaches is possible.
The more traditional solution for years was modeling of responses by the business analysts. This approach is still useful at the starting stage when there is not enough data.
The businesses, which evaluate the benefits of chatbots, have a different situation. Huge volumes accumulated from earlier customer interactions, large knowledge bases and product portfolios.
This is where using machine learning can not only help to classify intents and entities, but also to reveal efficient problem-solving scenarios. And using machine learning for data analysis even got a name “continuous learning”, enabling fast recognition of changing trends and revealing stories earlier not known.
Rich Content in Communication
Some users are sending simple requests, but there might be other scenarios:
- User asks about office or nearest branch location and bot has to describe address
- User has to choose one item of a limited set of choices
- User has to provide some data that should correspond to certain format or mask
Each of these cases can be settled with a text answer and text input from the user. But talking about the user experience, the cost of this “simplicity” could be too high. We can greatly enhance user satisfaction by providing augmented content. That includes map fragments with links, quick buttons with text, or even input boxes which ensure correct formatting.
Decision making
For simpler scenarios it is enough to provide an answer for the recognized intent. In complex scenarios it might be necessary to “sense” context and entities related to these scenarios.
Examples of such scenarios could be:
- booking a flight and definition of flight properties in any order comfortable for user, occasionally switching to inquiry about weather forecast in the destination location.
- preparing a bank payment and in meantime requesting cash balance on different accounts.
Capability of handling user input without predefined scenarios is a characteristic of “conversational chatbots”. While delivering superior user experience, requires significantly more engineering effort (in particular data science approaches).
Success of Scenario
The success of chatbots is measured by the number of successfully resolved cases. This is quite an objective measurement because it can be reflected with a “line in your budget”.
However, businesses should consider real impact of chatbots from a total volume of customer requests, keeping in mind the following “gears” between customer and business:
- Not all customers enjoy using chatbots. Some people still prefer speaking with humans, despite the fact that chatbots are available 24/7.
- NLU engines still have room for improvement. Understanding context and intent in English can be tricky due to slang, typos, and ambiguous situations. Even if a bot knows the answer, it may not always understand what the user is asking. When talking about languages other than English, business analysts should be aware of regional differences and specific details.
- Chatbots use information they are taught, either through rules set by analysts or machine learning. Some requests are too specific or complicated for them to handle.
In summary, we need to accurately assess how chatbots handle customer requests in a specific area. Success with chatbots differs by industry, so relying solely on them for business success is not practical.
Success with chatbots varies by industry, so it’s not realistic to rely on them completely for business success. However, even a small increase in customer satisfaction can benefit large businesses.
When Something Goes Wrong
Regardless of implementation, there are no “oracles” among chatbots, and sooner or later users may ask a question which cannot be answered by chatbot. For this case the minimum set of features should be:
- prepare a number of variations in expressions that describe inability to handle request, to sound more natural
- when user decides to end conversation – provide a possibility of feedback or contact information
- store conversation log for later analysis (in particular – by machine learning algorithms).
However, where possible, user experience could be enhanced with additional instruments that motivate user to stay in touch with the business until desired result is reached:
- possibility to transit to live chat with human support staff when chatbot cannot handle specific request
- as bots are designed for 24/7 use and human support staff is not always online it might be very helpful to use bot to schedule live contact within working hours in user-preferred channel.
Chatbots as Augmentation of Human Staff
When you transfer a chat to a human, it’s useful to include the user’s context, intentions, and chat history. This can help improve understanding of the situation and speed up response times. The bot on this platform can assist people by searching for answers in a private database. This makes it easier for humans to quickly find solutions.
A chatbot can be used as a personal assistant to remind employees about their appointments. This can be done through a corporate chat platform.
Continuous Improvements
Just because a conversation ends, doesn’t mean the journey is over. Any data collected from the chat should be stored, classified, and analyzed as a new experience. Every contribution to the data lake is valuable when used correctly. It doesn’t matter if it comes from chatbots, humans, or both.
Artificial intelligence and machine learning can process large amounts of data quickly. They can generate results and conclusions faster and more cost-effectively than traditional methods. This is another benefit of using these technologies.
Dialogue modeling
For businesses chatbot implementation usually starts with identification of known cases based on accumulated statistics, knowledge and priorities. Afterwards, continuous learning helps to improve chatbot gradually to face new challenges and match new requirements.
Identified requests need a response from key stakeholders like business analysts and subject matter experts. They have the most knowledge about business processes, terms, and language used in the business domain.
Crafting your Chatbot
Despite of many references above on using chatbot in customer support, there is a number of uses which could have even greater value for business:
- assistance in customer engagement on web-site or other channel, by analysis of user behavior and encouraging users to interact with bot and share their interests, habits and preferences and then generating lead for sales and marketing departments and transition to live chat with humans where possible
- bots can also perform a role of robo-sellers by analyzing customer requests and finding appropriate products or services; this role could also be a part of support scenario to offer upsell products in some cases
- business scenarios that require data collection from customers such as surveys, questionnaires, inquiries and other forms of customer-to-business data delivery in most cases can be elegantly resolved with chatbots, especially considering that chat is quite natural communication method of younger generations and significantly lowers cognitive pressure compared to long and complicated web-forms.
The backend of the bot solution needs to connect with other internal services and platforms to provide personalized service. This connection allows the bot to access the necessary information and functionality to deliver the desired experience to users.
Integrations need to be identified early on to create a clear plan and address any potential issues during implementation. Connecting CRM/ERP systems, knowledge bases, and other resources is typically done using service APIs.
Balance of Benefits and Risks
Chatbots provide numerous opportunities. However, it is crucial to also think about the risks involved.
This is especially important for large enterprises with strict security regulations. These enterprises are typically found in sectors like banking or healthcare.
When interacting with registered customers, bots need permission to access their data. They may use interactive elements to collect and display customer information.
Smaller businesses may benefit from using cloud-based SaaS/PaaS solutions. Larger companies in highly regulated industries, however, prefer on-premise setups. They do this to keep data exchange internal, reduce risks, and maintain control over processes. So, everything is dependent on your business case.
Summary
At Abto we prefer service-oriented approach focused on business objectives of our customers, so we would gladly consult your business about benefits which can be gained through implementation of chatbot and offer a roadmap of feature implementations to maximize value delivery on each step. According to our vision one of the key achievements of chatbots should be trust and satisfaction of your customers, which this trust should be gradually and continuously improved to reveal all benefits of recent technological advancements.
