System, computer-implemented method, and computer program product to receive a case by a deep question answering system, identify a policy relevant in generating a response to the case, the policy containing a set of criteria used in generating the response to the case, produce, by a first annotator, of a set of annotators, one or more relevant passages of the case, compute a criteria score for a first criterion, of the set of criteria, based on the one or more relevant passages of the case, an determine that the first criterion is met by the case when the criteria score for the first criterion exceeds a predefined threshold.