Intelligent agents are software programs that work in the background without direct human intervention to carry out specific tasks for an individual user, business process, or software application. The agent uses a limited built-in or learned knowledge base to accomplish tasks or make decisions on the user’s behalf, such as deleting junk email, scheduling appointments, or finding the cheapest airfare to California.
There are many intelligent agent applications today in operating systems, application software, email systems, mobile computing software, and network tools. Of special interest to business are intelligent agent bots that search for information on the Internet. Chapter 7 describes how shopping bots help consumers find products they want and assist them in comparing prices and other features.
Although some software agents are programmed to follow a simple set of rules, others are capable of learning from experience and adjusting their behavior using machine learning and natural language processing. Siri, a virtual assistant application on Apple’s iPhone and iPad, is an example. Siri uses natural language processing to answer questions, make recommendations, and perform actions. The software adapts to the user’s individual preferences over time and personalizes results, performing tasks such as getting directions, scheduling appointments, and sending messages. Similar products include Google Now, Microsoft’s Cortana, and Amazon’s Alexa.
Chatbots (chatterbots) are software agents designed to simulate a conversation with one or more human users via textual or auditory methods. They try to understand what you type or say and respond by answering questions or executing tasks. They provide automated conversations that allow users to do things like check the weather, manage personal finances, shop online, and receive help when they have questions for customer service. Vodafone, a multinational telecommunications company, uses a chatbot to answer 80,000 questions per month, reducing contact center calls for 75 percent of the customers it chats with. Vodafone staff use the chatbot to access accurate, up-to-date information on Vodafone products and services. Facebook has integrated chatbots into its Messenger messaging app so that an outside company with a Facebook brand page can interact with Facebook users through the chat program. Today’s chatbots perform very basic functions but will become more technologically advanced in the future.
Procter & Gamble (P&G) used intelligent agent technology to make its supply chain more efficient (see Figure 11.7). It modeled a complex supply chain as a group of semiautonomous agents representing individual supply chain components such as trucks, production facilities, distributors, and retail stores. The behavior of each agent is programmed to follow rules that mimic actual behavior, such as “order an item when it is out of stock.” Simulations using the agents enable the company to perform what-if analyses on inventory levels, instore stockouts, and transportation costs.
Using intelligent agent models, P&G discovered that trucks should often be dispatched before being fully loaded. Although transportation costs would be higher using partially loaded trucks, the simulation showed that retail store stockouts would occur less often, thus reducing the number of lost sales, which would more than make up for the higher distribution costs. Agent-based modeling has saved P&G $300 million annually on an investment of less than 1 percent of that amount.
Source: Laudon Kenneth C., Laudon Jane Price (2020), Management Information Systems: Managing the Digital Firm, Pearson; 16th edition.