Incident reporting systems help users to provide information about potential safety hazards. They, therefore, represent an important subset of the wider range of applications that support process improvement. The following pages identify a range of novel computational techniques that can be used to address problems of existing reporting systems. In particular, it is argued that computerassisted interviewing techniques, such as the familiar frame and script approaches, can guide the elicitation of incident reports. Probabilistic information retrieval systems reduce the classification problems that prevent attempts to index diverse reports in dynamic industries. Conversational casebased reasoning techniques can be used to avoid the problems of query formation that frustrate attempts to retrieve similar incidents. Finally, discourse-modeling techniques can be extended to represent the reasons why particular lessons have been learnt from particular incidents.