The EVA (espacios virtuales de aprendizaje, or virtual learning spaces) pro
ject applies artificial intelligence tools to teleteaching methods, in a wa
y that eliminates or mitigates the need for synchronous and in situ educati
on. (A) A taxonomy of the space of knowledge (also called 'Learning Space';
currently our prototype teaches M.Sc. courses in Computer Science) is form
ed and discretized. (B) EVA finds each student's initial knowledge state (t
hrough a computer examination:) and final (desired) knowledge state, and fr
om these, a particular learning trajectory is designed for that student. (C
) Personalized books (called polybooks, because they are formed by modules
(chapters) written in a variety of media) are armed by concatenating - alon
g the learning trajectory - modules from a large pool, and sent to the stud
ent through the net in a store-and-forward fashion. (D) EVA searches the ne
t for teaching material which has not been indexed in the discretized learn
ing space, using a tool (Clasitex) inside an agent that finds the main them
es or topics that an article (written in natural language) covers. (E) EVA
also schedules for each student synchronous activities (lectures in TV, tel
econferences, on-line question and answering sessions, chats). (F) EVA sugg
ests for each student suitable 'classmates' (students having similar learni
ng trajectories) in her town, as well as possible advisers (students or alu
mni having knowledge that the student is acquiring). The present status, pr
oblems, models and tools of EVA are presented. (C) 1998 Elsevier Science Lt
d. All rights reserved.