Abstract: Tabletop scenario co-piloting includes selecting a scenario as a subject of a tabletop scenario collaborative activity and tuning an initial prompt as a combination of the selected scenario and a directive to produce an indication of an adverse event associated with the selected scenario. The tuned initial prompt is submitted to an LLM which returns in response an indication of the adverse event for presentation by a business continuity management system in an associated user interface. A specification of a reaction to the adverse event is received in the user interface and a subsequent prompt is tuned with the reaction and submitted to the LLM. In reply, the LLM provides an indication of a further adverse event and the business continuity management system presents the indication of the further adverse event in the user interface. This process repeats as the basis of a tabletop scenario co-pilot supported exercise.

Abstract: Scenario generation includes establishing a communicative coupling between a computer-generated business continuity management user interface and a selected large language model (LLM). Scenario generation includes specifying an adverse event in the user interface and querying a database of scenario description records for an organization with the specified adverse event in order to receive a vector of relevant data to the specified adverse event. Scenario generation further includes first tuning a pre-determined LLM prompt with the vector to produce a specific LLM prompt for the specified adverse event and then submitting the specific LLM prompt to the selected LLM from over the communicative coupling. The selected LLM returns to the user interface scenario text referring to a plausible instance of the specified adverse event. Finally, scenario generation includes persisting the scenario text into persistent storage in connection with a specific scenario for use in a scenario simulation engine.

Abstract: Simulation for business continuity includes querying a scenario repository for a specific adverse event and responding to the query by selecting and retrieving from the repository infrastructure element objects that are associated with the specific adverse event. The simulation executes a Monte Carlo scenario test of the infrastructure element objects across a range of the susceptibility values through the computation of an average of the susceptibility values for each infrastructure element object for randomly selected different degrees of severity of the event. The simulation additionally executes a recovery simulation of the infrastructure element objects across a range of recovery times by computing an average recovery time for each infrastructure element object amongst the range of the recovery times.

Abstract: Scenario generation includes establishing a communicative coupling between a computer-generated business continuity management user interface and a selected large language model (LLM). Scenario generation includes specifying an adverse event in the user interface and querying a database of scenario description records for an organization with the specified adverse event in order to receive a vector of relevant data to the specified adverse event. Scenario generation further includes first tuning a pre-determined LLM prompt with the vector to produce a specific LLM prompt for the specified adverse event and then submitting the specific LLM prompt to the selected LLM from over the communicative coupling. The selected LLM returns to the user interface scenario text referring to a plausible instance of the specified adverse event. Finally, scenario generation includes persisting the scenario text into persistent storage in connection with a specific scenario for use in a scenario simulation engine.