This paper presents a design solution for a Personal Adaptive Web (PAW) agent which reduces information overload for Web users by autonomously retrieving documents that the user is interested in. The PAW agent is a personal assistant which learns different categories of Web documents that the user is interested in, then finds and suggests new similar documents to the user. It performs seven subtasks to achieve its goal. It (i) monitors the user while she is browsing the Web, (ii) determines the relevant documents that the user visits using fuzzy logic measures, (iii) textually analyses the relevant documents to obtain document vectors using a modified form of the inverse document frequency weight (IDFW) technique, (iv) classifies the document vectors into categories using unsupervised competitive learning, (v) scans the Web for similar documents, (vi) classifies the new document vectors using the trained neural network and (vii) decides whether the new documents should be referred to the user using fuzzy logic rules. In accomplishing the above seven subtasks, a real time database, automatic text analysis technique, competitive learning network and a fuzzy inference system are incorporated into the PAW agent.