Abstract: Embodiments are directed to surveying security environments. A subject index that includes entries may be generated based on a survey of a content system. A question of a client may be compared to entries in the subject index. A prompt associated with the content system may be generated based on the entries, the data sources, or the question. Query models may be employed to obtain data associated with the question from the data sources. Other prompts may be generated based on the data from the data sources to generate candidate answers based on the question and the data from the data sources. An evaluation prompt that includes the candidate answers and the question may be generated to rank the candidate answers for correctness. Answers may be determined based on the ranking of the candidate questions such that top ranked candidate answers are provided to the client.

Abstract: Embodiments are directed to surveying security environments. A subject index that includes entries may be generated based on a survey of a content system. A question a client may be matched to entries in the subject index. A prompt associated with the content system may be generated based on the entries, the data sources, or the question. Query models may be employed to obtain data associated with the question from the data sources. Other prompts may be generated based on the data from the data sources to generate candidate answers based on the question and the data from the data sources. An evaluation prompt that includes the candidate answers and the question may be generated to rank the candidate answers for correctness. Answers may be determined based on the ranking of the candidate questions such that top ranked candidate answers are provided to the client.

Abstract: Embodiments are directed to security analysis agents. Events associated with a computing environment may be provided. Prompt fragments may be determined based on the events. A prompt may be generated for a large language model (LLM) based on a prompt template and the prompt fragments such that the prompt fragments may be included in the prompt and provided to the LLM. Actions for evaluating the events may be determined based on the LLM response. These actions may be executed to evaluate the events. Portions of the response that correspond to the prompt fragments may be determined. A performance score may be determined for each prompt fragment based on its corresponding portion of the response such that the prompt may be modified to exclude a portion of the prompt fragments that have a performance score less than a threshold value.

Abstract: Embodiments are directed to security analysis agents. Events associated with a computing environment may be provided. Prompt fragments may be determined based on the events. A prompt may be generated for a large language model (LLM) based on a prompt template and the prompt fragments such that the prompt fragments may be included in the prompt and provided to the LLM. Actions for evaluating the events may be determined based on the LLM response. These actions may be executed to evaluate the events. Portions of the response that correspond to the prompt fragments may be determined. A performance score may be determined for each prompt fragment based on its corresponding portion of the response such that the prompt may be modified to exclude a portion of the prompt fragments that have a performance score less than a threshold value.