An Introductory Guide to Intelligent Agents

In this article intelligent agents are introduced, as well as a discussion of the possible impacts on business organisations of their usage.

Introduction to Intelligent Agents

Intelligent agents are computer programs that possess aspects of intelligence, and can act independently of their users. [1] These programs can be thought of as autonomous applications acting on the initial instructions of the user, in effect acting as an agent of the user.

The amount of intelligence in such agents may vary, but this term generally refers to the programs ability to act autonomously or to make decisions while attempting to carry out the user-assigned task. [1]

The term intelligent agent is used widely within the Information Technology (IT) industry to describe a wide-range of computer programs, many of which may have different design goals. For example, some agents are designed to undertake the entire task themselves; others work together while communicating with one another. Some agents are actually quite capable of learning and adapting to their environment, in order to carry out their tasks effectively. [2]

Intelligent agents are designed to assist users by acting on their behalf, normally carrying out time-consuming repetitive tasks such as accumulating information. [3] For busy managers and professionals, such time-consuming work can be delegated to intelligent agents, which will act on their instructions and report back findings at regular intervals.

Common Attributes of Intelligent Agents

While no definitive definition of what makes a computer program an intelligent agent currently exists, researchers have reached some consensus on the common attributes of intelligent agents:

  • Autonomy: an intelligent agent must be capable of working without human supervision.
  • Self-learning: an intelligent agent should be capable of changing their behaviour according to their accumulated knowledge.
  • Proactive: an intelligent agent should be capable of making decisions based on its own initiative.
  • Communication: an intelligent agent needs to be able to communicate with other systems and agents, while also communicating with the end user in natural language.
  • Co-operation: some of the more advanced intelligent agents should be able to act in unison with other agents to carry out complex tasks.
  • Mobility: an intelligent agent will need to be mobile, to enable it to travel throughout computer systems in order to accumulate knowledge and carry out tasks.
  • Goal Driven: all intelligent agents must have a goal, a user-defined purpose, and then act in accordance with that purpose.

Not all agents must possess every one of these attributes to be considered valid. For example, each agent is likely to have different knowledge, capabilities, reliability, resources and responsibilities that will all have a bearing on the design of the agent. [4]

What this means is that different agents may perceive the same data or event in different ways, dependent on the attributes and user agenda of the agent. As a consequence, careful consideration must be given to the business rules under which an agent will operate before it is deployed in a live environment.

Possible Usage of Agents in the Business Domain

If managers and professionals are to delegate tasks to intelligent agents, then what are the likely tasks to delegate Well, the usage of intelligent agents is only limited by two factors:

  1. The imagination of the designers of intelligence agents.
  2. The capabilities of the underlining technology supporting the development of intelligent agents.

As with many new technologies, the initial deployments often tend to be for demonstration purposes, with non-trivial deployments evolving over time when end users start to look for solutions to real problems, and cannot find these solutions in existing technologies, therefore turn to intelligent agent-based solutions. It is these deployments that will yield the most important and interesting work in the area.

The main technology-enabler for the wide spread use of intelligent agents is already in place: the Internet. In fact, due to the increasing complexity of the World Wide Web, where everything is available but services change by the second, intelligent agents are becoming necessary for user to make a cohesive view out of the information overload. [3] is a prime example of a business that has made extensive usage of intelligent agent technology. Thousands of activity and sales reports are automatically distributed to its associates each week, while digital sales clerks gently suggest to customers that people who bought a particular book also bought this other similar book by the same author. [4] The use of agents is not limited to the retail sector, however.

Applications that are highly suited for intelligent agent usage are [4]:

  • Data filtering and analysis.
  • Information brokering.
  • Condition monitoring and alarm generation.
  • Workflow management.
  • Personal assistance.
  • Simulation and gaming.

Working with only these general area headings, it is clear to see that the adaptation of intelligent agent technology could become widespread throughout organisations. For example, Human Resource (HR) professionals could use agents to data mine online recruitment websites for potential employees with certain pertinent skill sets, or stock brokers could use agents to monitor stock markets and news feeds to aid in risk management of funds. In short, the deployment of the technology is likely to be widespread and varied.

Limitations of Intelligent Agents

As with any technology-based solution, a number of limitations and concerns exist regarding the usage of intelligent agents. [5]

  • No overall system controller: intelligent agents may not be appropriate where there are global constraints that need to be enforced, due to the fact that each agent is effectively acting independently of any central controller. Applications requiring real-time responses are also inappropriate.
  • No global perspective: an agent can only make decisions based on locally accumulated knowledge, therefore an agent might be missing the "big picture" of a problem domain.
  • Trusting delegation: a user of an intelligent agent is effectively giving responsibility of data acquisition and decision making to a piece of computer code, therefore they must be sure that they can trust the agent to carry out the delegated task with integrity.

While some of these issues are technology related, others are side effects of the concept of intelligent agents itself. We cannot design an agent to be autonomous and capable of reaching its own decisions, only to decide that we now want to exert a central control over these agents, which is defeating the purpose of the concept.


The issue of control raises a fundamental philosophical concern with the widespread use of intelligent agents in business organisations: how much decision making controls are we willing to give up to an intelligent agent

In order to make business decisions based on the information provided in reports from intelligent agents, or to allow intelligent agents to carry out such business decisions, the intelligent agent developers must convince the users of such agents of the reliability of the software. While one hundred percent reliability is unrealistic in real world applications, a measure of dependability must be established.

Business decisions are driven by all kinds of information sources, many of which are unreliable, e.g. rumour and speculation. Nonetheless, business leaders often trust such information sources. Intelligent agents have no "hidden agenda": like any other computer program, they are simply and diligently carrying out a series of repetitive tasks, according to the users needs. As a result, human trust in intelligent agents is likely to increase in the years ahead.

The parallel has been made with intelligent agents and computer viruses, for example computer viruses act independently within computer networks just as agents do. The concern here is what would happen if an intelligent computer agent went rogue, returning false data in reports, or even worse actively causing damage on the Internet [1]

It is certainly possible, although agents from reputable developers are likely to include measures to prevent such things from happening. Less reputable developers have already shown a talent for modifying technology to meet ill aims, for example using automated web site crawling software, or spider bots, to harvest e-mail addresses from unsuspecting websites to be automatically added to spam mail lists.

Just as with any other technology that gives a business a competitive advantage, however short lived, intelligent agents are likely to follow a similar pattern of widespread adoption. If you know that your competitor uses them, then you are likely to want to follow suit, then before you know it everyone is using them. In-house development of highly specialised intelligent agents is likely to yield the most benefit where possible, as these agents can be highly suited to your needs, while the intellectual property of the agent code can be protected from competitors.


[1] Abbot, L & Siskovic (-), Intelligent Agents in Computer and Network Management, S,, Date Accessed: January 2005.

[2] Intelligent Agents Group (IAG) (-), A Survey on Intelligent Agents in Telecommunications,, Date Accessed: January 2005.

[3] Gilbert, D (1997), Intelligent Agents: the Right Information at the Right Time,, Date Accessed: January 2005.

[4] Farhoodi, F & Fingar, P (1997), Competing for the Future with Intelligent Agents,, Date Accessed: January 2005.

[5] Jennings, N.R. & Wooldridge, M (-), Application of Intelligent Agents,, Date Accessed: January 2005.

John Collins

I have been writing about web technology and software development since 2001. I am the developer of the Alpha Framework for PHP, and the personal productivity app. I love open source, technology, and economics.