With the vast quantity of information now available on the Internet, there is a need to manage this information by marking it with a semantic language, such as DARPA Agent Markup Language (DAML), and using intelligent search engines and other tools, in conjunction with ontology-based matching, to provide better search results and data manipulation capabilities. The aim of the semantic web is to make the current web more machine-readable, in order to allow intelligent agents to retrieve and manipulate pertinent information. The key goal of the DAML program is to develop a semantic web markup language that is sufficiently rich to support intelligent agents and other applications. Today's agents are not tightly integrated into the web infrastructure. If our goal is to have agents acting upon and conversing about web objects, they will have to be seamlessly integrated with the web, and take advantage of existing infrastructure whenever possible (e.g., message sending, security, authentication, directory services, and application service frameworks). We believe that DAML will be central to the realization of this goal.

In support of this claim, our UMBC agents group headed by Tim Finin has joint with the JHU/APL intelligent group headed by Jim Mayfield and a new business policies group at MIT/Sloan headed by Benjamin Grosof to create a new DAML-oriented research program. Our goal is design and prototype critical software components enabling developers to create intelligent software agents capable of understanding and processing information and knowledge encoded in DAML and other semantically rich languages.

For this, we are constructing a real, fielded application, ITTALKS, which supports user and agent interaction in the domain of talk discovery. It provides a simple web-driven infrastructure for interacting agents. In addition, ITTALKS serves as a platform for designing and prototyping other software components required to enable developers to create intelligent software agents capable of understanding and processing semantically rich information. To date, we have focused on developing the support and infrastructure required for intelligent agents to integrate into an environment of web browsers, servers, application server platforms, and associated supporting languages (e.g., WEB/SQL, WEBL), protocols (e.g., SSL, S/MIME, WAP, eSpeak), services (e.g., LDAP) and underlying technologies (e.g., Java, Jini, PKI).