> For the complete documentation index, see [llms.txt](https://propscreen.gitbook.io/propscreen/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://propscreen.gitbook.io/propscreen/introduction/solution-overview/user-personas.md). # User Personas ## Persona 1 - User of the LLM A user seeking unauthorized access to sensitive information (either intentionally or unintentionally) derived from a company's LLM. Sensitive information is any personal information or specific company information deemed to be confidential (e.g., sales information or customer lists). ### Intentional A malicious threat actor, could either be an insider threat such as an employee or an attacker from outside of the organization. Their motivation is to compromise the confidentiality of the data originally used to fine-tune the organization’s LLM and obtain access to data that they are not authorized to view or use. ### Unintentional An employee of the organization that has been given access to the LLM, but does not have access to view some of the information present in the response generated by the LLM. Their motivation is to use the LLM in order to perform their authorized work duties, however their prompts have resulted in a response from the LLM that has resulted in either an unauthorized accessibility to sensitive information that they are not authorized to view or produces an output containing personal information. ## Persona 2 - Company Security Analyst A company employee responsible for detecting insider threats, investigating incidents, and initiating responses to mitigate risks. This role may encompass different responsibilities depending on the scope of the issue, but primarily revolves around ensuring the confidentiality of the organization's sensitive information. Their actions may include: Monitoring LLM interactions, analyzing flagged responses, coordinating incident responses, reviewing access logs, investigating policy violations, and managing access controls. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://propscreen.gitbook.io/propscreen/introduction/solution-overview/user-personas.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.