Touching hands
2.3Toward Agent Applications and Intermediary Services
Navigation:

Back to the previous page Previous page

To the Table of Contents of this chapter Chapter ToC

To the Table of Contents of this paper Paper ToC

Today, information available through the Internet should - at least in theory - be "a mouse-click away" from whoever wants to get it. If you cannot find what you are looking for by casual browsing or by querying a search engine, the right information is bound to be pushed towards you.
As good as this may look in theory, the reality is different. Search engines often produce unsatisfying results, and the information pushed towards you does not (fully) cover what you are looking for.

The time never seemed to be better to (re-)introduce a familiar concept to move things to the next stage of evolution, the concept being that of "(intelligent) software agents"1. Already, more and more 'agent' applications are launched onto the market. However, most of them cannot qualify as real agents. The functionality they offer should better be called agent-like instead2, which is a too bad since the idea of agents really is a concept with much potential;

"Agents, it seems, have popped up overnight in all sorts of applications, leaving some of the most savvy users fuzzy about what they actually are. This confusion, as you might expect, has resulted in some vendors' using the words "agent" to describe programs that don't even come close to the true definition of an intelligent agent. [...] This fraudulent activity has given agents a bad name, for many potential users now scoff at the concept and view the technology merely as marketing hype.

But if you look harder, even beyond the agent implementation available on the PC today, you'll discover that true agent technology is exciting, feasible, and desperately struggling to find its way into the mainstream as an enabling technology."

from [PLAI97]

Many agree that agent - or at least agent-like3 - applications are becoming a necessity to be able to cope with the enormous amount of information that is available through the Internet; the question does no longer seem to be if there will be a considerable usage of agents, but rather when this will happen.
The frenzy around Push Technology seems to have fuelled agent developments in a special way, as several producers of Push applications have teamed up with producers of agent applications. Those producers saw that Push’s information channels are too restrictive and too limited to be of practical use to an increasing number of their clients.

"Just as content can be customised, so the interactive options offered to Web users can be customised. This type of customisation is more powerful and more subtle than ‘push’. By using agent-enhanced services to provide finely tuned interaction choices, a Web presence [can be developed] that lures and entices users rather than pushes at them."
from [OVUM97]

Most of the stand-alone agent applications that are being released are geared at searching the WWW or Usenet based on a group of keywords, concepts, or even entire questions stated in normal sentences.
Another area where agents are already used is that of assisting users while they use a software package. Microsoft's Office 97 suite has such agents, which are presented as different characters. These agents present all kinds of hints and tips to users as they are working with the software4. The agents can also called in for assistance by asking them questions in normal (natural language) sentences. When answering these questions, such things as the current user context are used to give the best possible answers and most relevant information.5

So, while most agent packages aren't that sophisticated at the moment, they already can relieve the average user of quite a lot of mundane tasks (which usually do not really require that much intelligence, but do require a lot of time or are just plain boring for a human to do);

"You can imagine thinking of an intelligent landscape inhabited not only by humans but by smartifacts - artifacts that are intelligent enough to have some degree of autonomy. [It] will be decades and decades before we have agents or devices intelligent enough to make people nervous. But we already have devices today that are sufficiently autonomous that they do things for us that are practical."
Paul Saffo in an interview published in the IBM Networking Forum

So, although current agents implementations do not really deserve the label "intelligent", what they will do is make people familiar with agents and with the tasks they are capable of doing, which is an important first step towards increased usage and acceptance of agents by a broad range of users.


Apart from software agents, another emerging development is the take-off of third parties (and of various other intermediary services) that assist people in satisfying their information needs. These services enable you to get news and information about any possible topic, not just the popular ones.
An interesting example of such a service is InfoWizard, where you can create search profiles. After choosing a category for the profile, you enter the concepts or keywords that best describe the information that is needed (InfoWizard will recognise composite terms like "information retrieval": it will not just search on the separate keywords "information" and "retrieval"). These concepts form a search query to which a name can be assigned. Depending on the selected service level6, you will receive an e-mail message whenever a report is ready. For clients of the service, this is very convenient as it is not necessary to stay online while waiting for the search results. Another plus are the information sources as they are used by InfoWizard: the service does not only get its information from the usual, free Web sources, but also from sources which require paid access (such as several pay-per-use databases). Any user that consults InfoWizard can now get information from such sources, without the need to subscribe to these sources himself (which would be an expensive affair). A third advantage is that the search results are not presented as a long list of document links, but in a report-like fashion (the result list contains not only document references, but (usually) the entire document text as well). To improve future search results, users can rate the retrieved documents on a per document basis.
It may be expected that more of such services will emerge. Some of these services will be free, as they are offered by such information intermediaries as public libraries or governments, whereas others will ask some kind of fee;

"As the Net matures, the decision to opt for a given information collection method will depend mostly on users. For which users will it then come to resemble a library, with a structured approach to building collections? And for whom will it remain anarchic, with access supplied by automated systems?"
from [LYNC97]

Large quantities of software agents combined with electronic intermediary-like programs (such as "Matchmakers" - see [HERM96]) can be used to further enhance and enlarge this new shackle in the information chain. Chapter three will elaborate further on these and other new ways to consume and convey information.


1= For more information on software agents, see [HERM96].
2= The stress is on "like" since they do not posses vital agent characteristics, e.g. the packages do not seem to learn from user input (such as which retrieved documents are looked at first), they show little or no proactivity, and they usually are not autonomous (i.e. the user has to activate them manually).
3= In the rest of this chapter the term "agents" will be used whereas, when looking at the current state of the technique, "agent-like" would be more appropriate. As it would be rather tedious to point out this aspect over and over again, we will refrain to the former term. In chapter three and five, a much closer look will be taken at 'real' agents and agent applications.
4= For instance, when they see that a user repeatedly performs a series of actions which could very well be done with a macro command, the agent will point this out to the user and will assist him - if needed - with the creation of the macro.
5= To answer user questions in the best possible way and assist them in using this suite, these agents rely on usage patterns as Microsoft has acquired them during in-house user test sessions. These tests were used to collect large amounts of statistical data about the way people usually use the software, and about the most common errors and problems (e.g. which topics are looked up the most in the suite's help files). When answering questions, agents uses these data to fine-tune the way in which they answer the question. There is a drawback to this approach for a certain group of users: those which use the suite in a way that strongly deviates from the way average users used in the user tests (e.g. expert or power users). They will find the agents assistance to be a nuisance (e.g. the agents gives them hints they already know) and "patronising".
6= InfoWizard will bill you depending on the stated preferences: it is possible to receive a standard report (which may cost one dollar) or an elaborate report (which will cost more). You can also chose to mark an information search as urgent (and thus more expensive) so that you will receive results within, say, an hour, whereas a normal search (which is less expensive) would yield results after a day.
On to the next page Next page
To the Hermans' Home Page Home Page
Chapter 2 - The Internet (of) Today "Desperately Seeking: Helping Hands and Human Touch" -
by Björn Hermans