Abstract: Embodiments are dynamic investigation playbooks. Events associated with activity in the computing environment may be obtained. Heritage playbooks may be collected based on characteristics of the events such that each heritage playbook includes heritage instructions for investigating the events. An analysis playbook may be obtained based on an analysis of the events such that the analysis playbook includes analysis instructions to automatically investigate the events. An updated analysis playbook may be obtained based on the analysis playbook and portions of the heritage playbooks such that the portions of the heritage playbooks may be included in the updated analysis playbook. An investigation of the events may be executed based on the updated analysis playbook such that actions may be executed based on the portions of the heritage playbooks.

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 perform automated threat hunting in computing environments. A threat hunt plan is obtained to guide collection of candidate evidence items from evidence sources. Portions of candidate evidence items are discarded based on relevance scores, and evidence items are determined from non-discarded portions. Threat indicators associated with the evidence items are identified based on criteria in the threat hunt plan. Threat profiles are obtained based on the evidence items and threat indicators such that threat profiles include threat assessment metrics and are included in a report. Collection agents may interface with system logs, network traffic captures, endpoints, databases, email services, or user activity records to gather evidence items based on time ranges, filtering criteria, or sampling rates.

Abstract: Embodiments manage context repositories in computing environments to enhance automated security analysis. Embodiments obtain context records containing supplemental information associated with security events and integrates them into prompts for large language models (LLMs) to generate severity scores for event classification. Embodiments apply criteria to invalidate outdated or unreliable context records based on age, source reliability, and usage frequency, then modifies prompts and repositories accordingly. Enhanced prompts incorporate context record summaries and entity relationship mappings to improve subsequent event analysis. Embodiments dynamically evaluates context records through quality filters, consolidates duplicates, and maintains audit trails with provenance tracking. User interfaces are dynamically transformed based on telemetry metrics and user feedback to optimize analyst workflows.

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.