With Internet taking an increasingly important place in our daily life (work, education, hobby), a huge amount of information is now available. We suggest that four points should be considered when developing new information retrieving systems: a) taking information in its entirety (interpretation), b)managing multimedia information in an integrated Rap c) reusing already available tools and d) tailoring information to single users. We propose here our framework for endowing a software agent with the capability to personalize itself to its users through interaction and perform tasks that involve subjective factors. We describe K-DIME, a software prototype that can retrieve material ii-om the Web on the basis of both objective and subjective features of the content. Being capable of bootstrapping a new user model from the model of a user with similar profile, K-DIME significantly reduces the workload generally associated with an online learning phase. Through continuous adaptation driven by specific patterns of interaction with the user, K-DIME can cope with the intrinsic variability of subjective impressions. We discuss its performance in a scenario in which users retrieve pictures to be put on a greeting card according to a given subjective impression they wish to convey.