A chatbot -- sometimes referred to as a chatterbot -- is programming that simulates the conversation or "chatter" of a human being through text or voice interactions. Chatbot virtual assistants are increasingly being used to handle simple, look-up tasks in both business-to-consumer (B2C) and business-to-business (B2B) environments. The addition of chatbot assistants not only reduces overhead costs by making better use of support staff time, it also allows companies to provide a level of customer service during hours when live agents aren't available.

Chatbots can have varying levels of complexity, being either stateless or stateful. A stateless chatbot approaches each conversation as if it was interacting with a new user. In contrast, a stateful chatbot can review past interactions and frame new responses in context. Adding a chatbot to a company's service or sales department requires low or no coding. Today, a number of chatbot service providers allow developers to build conversational user interfaces for third-party business applications.

How chatbots work

Perhaps the most important aspect of implementing a chatbot is selecting the right natural language processing (NLP) engine. If the user interacts with the bot through voice, for example, then the chatbot requires a speech recognition engine. Business owners also must decide whether they want structured or unstructured conversations. Chatbots built for structured conversations are highly scripted, which simplifies programming but restricts the kinds of things that the users can ask.

In B2B environments, chatbots are commonly scripted and used to respond to frequently asked questions or perform simple, repetitive calls to action. In sales, a chatbot may be a quick way for sales reps to get phone numbers. 

Chatbots can also be used in service departments, assisting service agents in answering repetitive requests. For example, a service rep might provide the chatbot with an order number and ask when the order was shipped. Generally, once a conversation gets too complex for a chatbot, the call or text window will be transferred to a human service agent.

Chatbots such as ELIZA and PARRY were early attempts at creating programs that could at least temporarily fool a real human being into thinking they were having a conversation with another person. PARRY's effectiveness was benchmarked in the early 1970s using a version of a Turing test; testers only made the correct identification of a human versus a chatbot at a level consistent with making a random guess.

Chatbots have come a long way since then. They are built on artificial intelligence (AI) technologies, including deep learning, natural language processing and machine learning (ML) algorithms, and require massive amounts of data. The more an end user interacts with the bot, the better voice recognition becomes at predicting an appropriate response.

Types of chatbots

Since chatbots are still a relatively new technology, there is debate around the amount and classification of the available types. However, some common types of chatbots include:

Scripted or quick reply chatbots - These are the most basic chatbots; they act as a hierarchical decision tree. These bots interact with users through a set of predefined questions that progress until the chatbot has answered the user's question. Similar to this chatbot is the menu-based chatbot that requires users to make selections from a predefined list, or menu, to provide the bot with a deeper understanding of what the customer is looking for.

Keyword recognition-based chatbots - These chatbots are a bit more complex; they attempt to listen to what the user types and respond accordingly using keywords picked up from customer responses. Customizable key words and AI are combined in this bot to provide an appropriate response to users. Unfortunately, these chatbots struggle when faced with repetitive keyword use or redundant questions.

Hybrid chatbots - These chatbots combine elements of menu-based and keyword recognition-based bots. Users can choose to have their questions answered directly, but can also access the chatbot's menu to make selections if the keyword recognition process produces ineffective results.

Contextual chatbots - These chatbots are more complex than those listed above and require a data-centric focus. They use ML and AI to remember conversations and interactions with users, and then use these memories to grow and improve over time. Instead of relying on keywords, these bots use what customers ask for and how they ask it to provide answers and self-improve.

Voice-enabled chatbots - This type of chatbot is the future of chatbot technology. Voice-enabled chatbots use spoken dialogue from users as input that prompts responses or creative tasks. They can be created using text-to-speech (TTS) and voice recognition application program interfaces (APIs). Current examples include Amazon Alexa and Apple's Siri.

Examples of chatbot uses

Chatbot use is on the rise, both in the business and consumer markets. As chatbots improve, consumers have less to quarrel about while interacting with them. Between advanced technology and a societal transition to more passive, text-based communication, chatbots help fill a niche that phone calls used to fill.

Chatbots have been used in instant messaging applications and online interactive games for many years, but have recently segued into B2C and B2B sales and services. Chatbots can be added to a buddy list or provide a single game player with an entity to interact with while awaiting other "live" players. If the bot is sophisticated enough to pass the Turing test, the person may not even know they are interacting with a computer program.

In sales, chatbots are being used to assist consumers shopping online, either by answering noncomplex product questions or providing helpful information that the consumer could later search for, including shipping price and availability. Chatbots are also used in service departments, assisting service agents in answering repetitive requests. Once a conversation gets too complex for a chatbot, it will be transferred to a human service agent.

Chatbots are also used as virtual assistants. Apple, Amazon, Google and Microsoft all have forms of virtual assistants. Apps, such as Apple's Siri and Microsoft's Cortana, or products, like Amazon's Echo with Alexa or Google Home, all play the part of a personal chatbot.

Why chatbots are important

The timesavings and efficiency derived from AI chatbots conversing and answering reoccurring questions is attractive to companies looking to increase sales or service productivity.

A chart revealing a chatbot vs. conversational agent vs. virtual assistant.
A chart displaying the differences between a chatbot, conversational agent and virtual assistant.

As consumers continue to move away from traditional forms of communication, chat-based communication methods are expected to rise. Chatbot-based virtual assistants are increasingly used to handle simple tasks, freeing human agents to focus on higher-profile service or sales cases.

How chatbots are changing customer experience

The rapidly evolving digital world is altering and increasing customer expectations. Many consumers expect companies to be available 24/7 and feel that the customer experience provided by a company is just as important as the quality of products or services they provide. Furthermore, buyers are more informed about the variety of available products and services and, consequently, are less likely to remain loyal to a specific brand. Chatbots are a response to these changing needs and rising expectations. They are replacing live chat and other previously used forms of contact, such as emails and phone calls.

Chatbots have the potential to enhance the customer experience by:

  • reducing customer waiting time and providing immediate answers;
  • providing customers with 24/7 customer support;
  • removing the threat of unpleasant human-to-human interactions that are dictated by the mood and emotions of both the service or sales representative and the customer;
  • minimizing the stress and annoyance that some customers feel when having to contact customer support by reducing wait time and streamlining the conversation;
  • improving the redirection of customer queries;
  • advancing brand personality by adding customized elements to the chatbot; and
  • personalizing each customer experience with the use of AI-enabled chatbots.

Additionally, major technology companies, such as Google, Apple and Facebook, have developed their messaging apps into chatbot platforms that can handle services like orders, payments and bookings. Furthermore, when used with messaging apps, chatbots present users with the ability to find answers no matter where they are and regardless of the device they're using. The interaction is also easier because customers do not have to fill out forms or waste minutes searching for answers within long content.

Benefits of using chatbots

In addition to the benefits addressed above concerning the impact of chatbots on customer experience, businesses also pull various advantages. For example, improved customer experience and more satisfied customers increase the likelihood that a company will continue to draw profit from loyal customers. Also, chatbots can carry out simultaneous conversations with thousands of buyers. This increases business productivity, while also eliminating the need for a customer to wait for a free representative. Other benefits include:

Cost effective - Chatbots are a one-time investment that is faster and cheaper than creating a dedicated, cross platform app or hiring additional employees. In addition to reducing employee costs, chatbots will also reduce costly problems caused by human error. Furthermore, the cost of user acquisition also decreases since chatbots are easily and immediately available and respond within seconds.

Saves time - Chatbots can automate tasks that must be performed frequently and at specific times. This provides human employees with more time to focus on other important tasks. Furthermore, the ability of chatbots to provide fast answers prevents customers from waiting to receive responses.

Proactive customer interaction - In the past, companies relied on passive customer interaction and waited for the buyer to reach out to them first. Chatbots provide organizations with the ability to be proactive with their interactions by initiating conversations and monitoring how customers use their websites and landing pages. Information gathered from observed customer activities can then be used to offer incentives specific to a buyer, help users navigate the site and answer future questions.

Monitor and analyze consumer data - Chatbots collect feedback from each interaction that can help businesses improve their services and products or optimize their website. They can also track consumer behaviors and purchasing patterns by recording user data. This information can provide companies with greater insight into how to better market their products and services, as well as common obstacles that customers face during the buying process.

Improves customer engagement - Most companies are already engaging their customers through social media. Chatbots can be used to make this engagement more interactive. Furthermore, buyers rarely talk to the people within businesses. Chatbots open a channel of communication where customers can engage without the stress of interacting with another person.

Eases scalability to global markets - Chatbots can solve customer concerns and queries in multiple languages. Furthermore, their 24/7 access allows them to be used regardless of the customer's time zone.

Expands the customer base - Chatbots can improve lead generation, qualification and nurturing. Throughout the buyer's journey, they can ask questions and provide information that may persuade the user and create a lead. Chatbots will then provide potential customer information to the sales team that can use it to engage with the leads. The bots can then improve conversion rates by ensuring the lead's journey flows in the right direction -- toward a purchase. Finally, chatbots can help sales teams determine if a lead is qualified or not using identified key performance indicators (KPIs), such as budget, timeline and resources. This will prevent companies from wasting time on unqualified leads and time-consuming customers.

Challenges of using chatbots

While chatbots improve customer experience and benefit organizations, they also present various challenges. One of the biggest challenges is that chatbot technology is still new and, therefore, it faces new obstacles that companies may not know how to deal with. Fortunately, AI-enabled bots can learn from each interaction and improve their own behaviors. Unfortunately, this process can cost businesses a lot of money if the initial interactions cause customers to disengage and turn away.

Chatbot security is another struggle faced. Users must trust the chatbot enough to share their personal data. Therefore, companies must ensure that their chatbots are designed to only request relevant data, as well as securely transmit that data over the internet. Furthermore, the chatbot design should be secure and able to prevent hackers from gaining access to the chat interface.

Additional challenges include:

  • Varieties in the way people type their message can make it hard to understand their intention. Chatbots must be able to deal with both long and short sentences, as well as chat bubbles with lengthy content versus multiple very short submissions.
  • The different ways in which humans talk can also be difficult for a chatbot to understand. For example, the user may use slang, misspell words and short form or acronyms. Unfortunately, NLP is limited and cannot fully resolve this challenge.
  • Human beings are random and user behavior is controlled by emotions and moods; users may quickly change their minds. After initially asking for a suggestion, they might switch to wanting to give a command instead. Chatbot technology must be able to adapt to and understand this element of randomness and spontaneity.

Finally, users always want the best experience, but are rarely satisfied. They always want the chatbot to be better than it currently is. This means that companies employing chatbots need to consistently update and improve them to ensure users are satisfied and feel like they're talking to a reliable, smart source.

Future of chatbots

Chatbots are expected to continue growing in popularity. A survey from computer software company Oracle found that 80% of brands intend to incorporate chatbots by 2020.

Artificial intelligence and machine learning will continue to evolve, offering new capabilities to chatbots and introducing a new level of text and voice-enabled user experiences that will continue to transform the customer experience. These improvements will also impact data collection and will offer deeper customer insights that can lead to predictive buyer behaviors.

Voice solutions are expected to become a common and necessary part of the IT ecosystem. Increased focus is being placed on developing a voice-based chatbot that can act as a conversational agent, understand numerous languages and respond in that same language.

This was last updated in December 2019

Continue Reading About chatbot

Dig Deeper on Contact center software and applications