Definition

chatbot

What is a chatbot?

A chatbot is a software or computer program that simulates human conversation or "chatter" through text or voice interactions.

Users in both business-to-consumer (B2C) and business-to-business (B2B) environments increasingly use chatbot virtual assistants to handle simple tasks. Adding chatbot assistants reduces overhead costs, uses support staff time better and enables organizations to provide customer service during hours when live agents aren't available.

How do chatbots work?

Chatbots have varying levels of complexity, being either stateless or stateful. Stateless chatbots approach each conversation as if interacting with a new user. In contrast, stateful chatbots can review past interactions and frame new responses in context.

Adding a chatbot to a service or sales department requires low or no coding. Many chatbot service providers allow developers to build conversational user interfaces for third-party business applications.

A critical aspect of chatbot implementation 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 what users can ask. In B2B environments, chatbots are commonly scripted to respond to frequently asked questions or perform simple, repetitive tasks. For example, chatbots can enable sales reps to get phone numbers quickly.

Why are chatbots important?

Organizations looking to increase sales or service productivity may adopt chatbots for time savings and efficiency, as artificial intelligence (AI) chatbots can converse with users and answer recurring questions.

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 move away from traditional forms of communication, many experts expect chat-based communication methods to rise. Organizations increasingly use chatbot-based virtual assistants to handle simple tasks, allowing human agents to focus on other responsibilities.

How have chatbots evolved?

Chatbots such as ELIZA and PARRY were early attempts to create programs that could at least temporarily make a real person think they were conversing with another person. PARRY's effectiveness was benchmarked in the early 1970s using a version of a Turing test; testers only correctly identified a human vs. a chatbot at a level consistent with making random guesses.

Chatbots have come a long way since then. Developers build modern chatbots on AI technologies, including deep learning, NLP and machine learning (ML) algorithms. These chatbots require massive amounts of data. The more an end user interacts with the bot, the better its voice recognition predicts appropriate responses.

Chatbot use is on the rise in 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.

Types of chatbots

As chatbots are still a relatively new business technology, debate surrounds how many different types of chatbots exist and what the industry should call them.

Some common types of chatbots include the following:

Scripted or quick reply chatbots. As the most basic chatbots, they act as a hierarchical decision tree. These bots interact with users through predefined questions that progress until the chatbot answers the user's question.

Similar to this bot 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 needs.

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 from customer responses. This bot combines customizable keywords and AI to respond appropriately. Unfortunately, these chatbots struggle 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 or use the chatbot's menu to make selections if keyword recognition is ineffective.

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

Voice-enabled chatbots. This type of chatbot is the future of this technology. Voice-enabled chatbots use spoken dialogue from users as input that prompts responses or creative tasks. Developers can create these chatbots using text-to-speech and voice recognition APIs. Examples include Amazon Alexa and Apple's Siri.

A chart detailing language processing issues that chatbots face.
A chart laying out potential language barriers that face chatbots.

How do businesses use chatbots?

Chatbots have been used in instant messaging apps and online interactive games for many years and only recently segued into B2C and B2B sales and services.

Organizations can use chatbots in the following ways:

  • Online shopping. In these environments, sales teams can use chatbots to answer noncomplex product questions or provide helpful information that consumers could search for later, including shipping price and availability.
  • Customer service. Service departments can also use chatbots to help service agents answer repetitive requests. For example, a service rep might give the chatbot an order number and ask when the order shipped. Generally, a chatbot transfers the call or text to a human service agent once a conversation gets too complex.
  • Virtual assistants. Chatbots can also act 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.

How are chatbots changing businesses and CX?

The rapidly evolving digital world is altering and increasing customer expectations. Many consumers expect organizations to be available 24/7 and believe an organization's CX is as important as its product or service quality. Furthermore, buyers are more informed about the variety of products and services available and are less likely to remain loyal to a specific brand.

Chatbots serve as a response to these changing needs and rising expectations. They can replace live chat and other forms of contact, such as emails and phone calls.

Chatbots can enhance CX in the following ways:

  • reduce customer wait times and provide immediate answers;
  • offer customers 24/7 support;
  • remove the potential for unpleasant human-to-human interactions that moods and emotions of both the service or sales representative and the customer dictate;
  • reduce wait times and streamline conversations to minimize the potential for customers' stress and annoyance;
  • improve the redirection of customer queries;
  • add customized elements to the chatbot to advance brand personality; and
  • personalize CX with AI-enabled chatbots.

Additionally, major technology companies, such as Google, Apple and Facebook, have developed their messaging apps into chatbot platforms to handle services like orders, payments and bookings. When used with messaging apps, chatbots enable users to find answers regardless of location or the devices they use. The interaction is also easier because customers don't have to fill out forms or waste time searching for answers within the content.

What are the benefits of using chatbots?

In addition to chatbots' benefits for CX, organizations also gain various advantages. For example, improved CX and more satisfied customers due to chatbots increase the likelihood that an organization will profit from loyal customers.

Other benefits include the following:

  • Can hold multiple conversations at once. Chatbots can converse simultaneously with thousands of buyers. This increases business productivity and eliminates wait times.
  • Cost-effective. A chatbot is a faster and cheaper one-time investment than creating a dedicated, cross-platform app or hiring additional employees. In addition, chatbots can reduce costly problems caused by human error. User acquisition costs also decrease with a chatbot's ability to respond within seconds.
  • Saves time. Chatbots can automate tasks performed frequently and at specific times. This gives employees time to focus on more important tasks and prevents customers from waiting to receive responses.
  • Proactive customer interaction. In the past, organizations relied on passive customer interaction and waited for buyers to reach out first. With chatbots, organizations can interact proactively, as bots can initiate conversations and monitor how customers use the websites and landing pages. Organizations can then use the information gathered from monitoring to offer specific incentives to buyers, help users navigate the site and answer future questions.
  • Monitors and analyzes consumer data. Chatbots collect feedback from each interaction to help businesses improve their services and products or optimize their websites. Bots can also record user data to track behaviors and purchasing patterns. This information can offer organizations 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 already engage their customers through social media. Chatbots can make this engagement more interactive. Buyers rarely talk to the people within businesses, so chatbots open a communication channel 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. Their 24/7 access enables customers to use them regardless of time or time zone.
  • Expands the customer base. Chatbots can improve lead generation, qualification and nurturing. Chatbots can ask questions throughout the buyer's journey and provide information that may persuade the user and create a lead. Chatbots can then provide potential customer information to the sales team, who can engage with the leads. The bots can improve conversion rates and ensure the lead's journey flows in the right direction -- toward a purchase.
  • Measures lead qualifications. Chatbots can help sales teams determine a lead's qualifications using identified key performance indicators, such as budget, timeline and resources. This can prevent companies from wasting time on unqualified leads and time-consuming customers.

What are the challenges of using chatbots?

While chatbots improve CX and benefit organizations, they also present various challenges.

These challenges include the following:

  • New technology, new obstacles. Chatbot technology is still new and faces obstacles that organizations may not know how to handle. While AI-enabled bots can learn from each interaction and improve their behaviors, this process can cost organizations a lot of money if the initial interactions cause customers to disengage and turn away.
  • Security. Users must trust the chatbot enough to share personal data. Therefore, organizations must ensure they design their chatbots to only request relevant data and securely transmit that data over the internet. Chatbots should have secure designs and be able to prevent hackers from accessing chat interfaces.
  • Varieties in how people type their messages. This can lead to misunderstood intentions. Chatbots must handle both long and short sentences, as well as chat bubbles with lengthy content versus multiple short submissions.
  • The different ways in which humans talk. Chatbots can struggle to understand these variations. For example, the user may use slang, misspell words or use acronyms. Unfortunately, NLP is limited and cannot fully resolve this challenge.
  • Unpredictable human behavior, moods and emotions. Humans are random and emotions and moods often control user behavior, so users may quickly change their minds. After initially asking for a suggestion, they might want to give a command instead. Chatbots must adapt to and understand this randomness and spontaneity.
  • User satisfaction. Users always want the best experiences but are rarely satisfied. They always want the chatbot to be better than it currently is. This means organizations employing chatbots must consistently update and improve them to ensure users feel like they're talking to a reliable, smart source.

Future of chatbots

Many experts expect chatbots to continue growing in popularity. In the future, AI and ML will continue to evolve, offer new capabilities to chatbots and introduce new levels of text and voice-enabled user experiences that will transform CX. These improvements may also affect data collection and offer deeper customer insights that lead to predictive buyer behaviors.

Voice services have also become common and necessary parts of the IT ecosystem. Many developers place an increased focus on developing voice-based chatbots that can act as conversational agents, understand numerous languages and respond in those same languages.

This was last updated in November 2021

Continue Reading About chatbot

Dig Deeper on Contact center software and applications

SearchContentManagement
SearchUnifiedCommunications
SearchDataManagement
SearchEnterpriseAI
SearchERP
Close