> For the complete documentation index, see [llms.txt](https://www.kauneonga.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.kauneonga.com/docs/ai/admin-ai/admin-ai.md). # Admin AI How Liberty Admin AI supports internal administrative workflows. Admin AI supports selected internal administrative workflows in Liberty. It helps admins and supervisors move faster on routine account work while keeping review and control in place. {% hint style="info" %} Availability may depend on your account configuration. Contact your account manager or if you need access. {% endhint %} ### What Admin AI supports Admin AI is designed for structured administrative workflows. Common uses include: * creating or updating client account setup * revising scripts, schedules, and routing rules * reviewing message, voicemail, and call activity * helping supervisors and admins move faster through repeatable changes ### How Admin AI and MCP relate Admin AI is the administrative workflow layer. It defines the kind of work Liberty can support for admins and supervisors. Liberty MCP is the connection layer for external assistants. Use MCP when you want to access Admin AI workflows from tools like ChatGPT or Claude. ### Supported assistants When Admin AI is used through an external assistant, Liberty currently supports: * [ChatGPT](/docs/ai/admin-ai/mcp/chatgpt.md) * [Claude](/docs/ai/admin-ai/mcp/claude.md) Connection steps vary by assistant and workspace. For setup details, see [Liberty MCP](/docs/ai/admin-ai/mcp.md). ### How access works Admin AI uses your existing Liberty access model. This means: * you sign in with your Liberty admin account * existing role permissions still apply * two-factor authentication is honored when enabled * changes require review before they are applied Admin AI does not expand what a user can see or change. ### Common use cases Admin AI is a strong fit for work such as: * setting up a new client account * updating holiday or after-hours routing * revising intake, dispatch, or escalation scripting * reviewing recent message, voicemail, and call activity * preparing repeatable admin changes before approval ### Example prompts Example requests include: * "Set up a new client account for a dental practice." * "Update holiday routing for this account." * "Show urgent messages from yesterday." * "Draft an after-hours intake script for an HVAC client." ### Where it fits best Admin AI works best when the task is: * structured * repeatable * tied to clear account rules * appropriate for admin review It is less useful for exception-heavy work or changes that need detailed operational judgment. ### Security and privacy Admin AI follows the same core access boundaries as the rest of Liberty. This includes: * access limited by user role and account permissions * encrypted traffic in transit * activity logging for administrative actions * the same handling expectations applied to client and message data in Liberty ### Getting started If Admin AI is enabled for your organization, start with a clear admin task and the right account context. If you are using ChatGPT or Claude, connect through [Liberty MCP](/docs/ai/admin-ai/mcp.md) and sign in with your Liberty admin account. If you need help with access or setup, contact . ### Operational guidance Start with clear account context and specific requests. The best results come from well-defined workflows, clear routing rules, and admin review before changes are finalized. --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://www.kauneonga.com/docs/ai/admin-ai/admin-ai.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.