Qualitatively enhanced access to data collections requires a more meaningful interface which endows the users with personal agents that are easily adapt-able to the users’ individual retrieval preferences. Tracking individual needs of users leads to personal digital assistance that appears in the system's inter-action mode as the user’s personal software agent. The main objective of per-sonal assistance as envisaged here is enabling the system to give the users recommendations that are derived from best practice in searching for informa-tion. Best practice reflects the knowledge about how users perform successful retrieval activities and attempt to define the best ways of searching large document collections. Best practices are developed on an individual as well as on a community base. The model presented here was developed for the information system IRAIA, a portal for economic information from huge data collections of Economic Re-search Institutes (ERI) and National Statistical Institutions (NSI). The per-sonal agent draws on IRAIA's model of context-oriented retrieval and ob-serve, record and analyse the users' search and navigation by applying con-cepts of the respective taxonomies.