In the WWW2 (2. Web Generation) users can look up content in the Web with the help of browsers which are presentation services (e.g. Firefox) and find documents via the use of specific information retrieval services (e.g. Google).
In the Semantic Web (WWW3) this is handle somehow different in a different way. The user have on their device (e.g. desktop computer, notebook, mobile, etc.)
some kind of Personal Assistant. This Personal Assistant will make use of intelligent infrastructure services and these services are accessing the web documents and they are collecting the information that is relevant for the user. The personal assistant will decide how to connect the information and how to present it to the user.
Today the World Wide Web consists of distinct, isolated islands of data and Metadata. In the near future the availiablity of critical mass of data and Metadata for use by Intelligent Agents that act on behalf of human users. These Agents would identify, propose and capture new opportunities to assist human users in satisfying ther goals, by traversing and acting on this semantically rich and abundant information. Agents learn from a human's goals and preferences, collaborate with other agents, mine semantic Content, identify new opportunity for actions, propose them and finally transact them, whil always informing the human.