For ontologies represented as Description Logic Tboxes, optimised DL reasoners are able to detect logical errors, but there is comparatively limited support for resolving such problems. One possible remedy is to weaken the available information to the extent that the errors disappear, but to limit the weakening process as much as possible. The most obvious way to do so is to remove just enough Tbox sentences to eliminate the errors. In this paper we propose a tableaulike procedure for finding maximally concept-satisfiable terminologies represented in the description logic ALC. We discuss some optimisation techniques, and report on preliminary, but encouraging, experimental results.