Chatbots are computer programs that simulate human conversations by using artificial intelligence to respond to questions and supply relevant information. A growing number of companies are relying on chatbots to streamline and improve their customer service. Read on to find out more about chatbots, including the different types of chatbots and some chatbot innovations.

An infographic defining and explaining the term "chatbot."
Image source: The Motley Fool

What are they?

What are chatbots?

A chatbot is a computer program that uses artificial intelligence to imitate a conversation with a human, generally through online text or voice applications. Chatbots range widely in sophistication, from text messages that answer a simple query with a “yes” or “no” to programs that are capable of having a lighthearted conversation.

Chatbots have their origins in work done by famed mathematician Alan Turing, who created a test to classify machines as intelligent, with the main criteria being that a person couldn’t tell if they were communicating with a human or a machine. Barely a decade after Turing’s death in 1954, a researcher at the Massachusetts Institute of Technology’s Artificial Intelligence Laboratory developed ELIZA, a program capable of responding to questions like a psychotherapist.

The programs have continued to evolve, along with the explosive growth of applications that use artificial intelligence. Only a few short years ago, a question about the weather to a chatbot might result in a simple forecast. These days, a chatbot might go so far as to suggest packing an umbrella and setting the alarm clock a little early to account for a slower commute.

Types

Types of chatbots

Software giant Oracle (ORCL 2.02%) defines two main types of chatbots:

Task-oriented chatbots: These programs have one function. They use rules, natural language processing, and a small amount of machine learning to generate responses to customer questions. They’re the most common type of chatbot. They can be used to provide basic information to customers, such as hours of operation for a business, policies for exchanges and returns, and account information.

Data-driven and predictive chatbots: These are often more sophisticated and interactive versions of chatbots that can learn user needs over time and even anticipate future requirements. Common examples are Siri, the virtual assistant created by Apple (AAPL -0.35%), and Alexa, the digital helper from Amazon (AMZN 3.43%).

Related investing topics

Example

Chatbot example

Although most attention lately has focused on ChatGPT, an AI-driven tool released in 2022 by OpenAI, both large and small companies have been using increasingly sophisticated chatbots for several years now.

Consider the often not-so-humble cup of Starbucks (SBUX 0.47%) coffee. The Seattle-based coffee giant reports that 25% of all transactions are conducted as mobile orders that are made through its app -- roughly 1 million cups of coffee every day of the year.

The chatbot, which is part of its mobile app, first appeared in 2017 and was designed to cut down on everyone’s favorite pastime of standing in an endless Starbucks line. The chatbot now supports natural language processing, so customers can make orders by voice and text. Payments are made with a linked credit card or gift card, and the order can be sent to the closest store. The chatbot’s artificial intelligence can even anticipate whether it’s a caramel frappuccino or grande Americano kind of day for you.

John Mackey, former CEO of Whole Foods Market, an Amazon subsidiary, is a member of The Motley Fool’s board of directors. The Motley Fool has positions in and recommends Amazon, Apple, Oracle, and Starbucks. The Motley Fool has a disclosure policy.