Nowadays, there is an increasing number of software applications offering task-based interactions through mobile devices or (directly) via the surrounding technological environment. Such interactions, which are difficult to assess with traditional user evaluation techniques due to their volatility, are usually recorded in dedicated interaction logs, which are then sent back to the software developers who must make sense of them. To date, log studies are mainly used to extract user behaviours from interaction logs for profiling purposes, or to compare such behaviors across different system variants. In this paper, we present a novel approach based on a declarative specification of interaction models that exploits logs for identifying exactly what has gone wrong during a user interaction, detecting which user actions may have caused usability issues and suggesting reparative actions for solving them.