> For the complete documentation index, see [llms.txt](https://planck-ai.gitbook.io/planck-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://planck-ai.gitbook.io/planck-ai-docs/documentation/getting-started-1/workspaces.md). # Workspaces A workspace is the main container for working in Planck AI. Use workspaces to organize users, documents, databases, cloud integrations, conversations, and permissions around a team, client, project, or business function. ### What a workspace contains A workspace can contain: * Uploaded documents * Synced cloud files * Connected databases * Conversations * Users and roles * API access * Integration-specific settings Most user activity in Planck AI happens inside a workspace. ### Common workspace examples Organizations can create workspaces for different use cases, teams, or clients. Examples: * Finance * Operations * Customer Support * Network Planning * Legal * Procurement * Client-specific workspace * Project-specific workspace ### Documents inside a workspace Documents uploaded or synced into a workspace become available for search and question answering inside that workspace. Supported file types may include: * PDF files * Excel files * CSV files * Text files Users can ask questions about one document, multiple documents, or the broader workspace context. ### Databases inside a workspace A workspace can also be connected to a database integration. Once connected, users can ask natural-language questions about structured data. Example questions: ``` Show monthly revenue for the last two quarters. ``` ``` Which suppliers had the highest spend this month? ``` ``` Break this down by region. ``` ### Conversations inside a workspace A conversation is a chat thread inside a workspace. Users can ask a question, review the answer, and then ask follow-up questions with context from the previous messages. Example questions: ``` Summarize this document. ``` ``` Now show the same result as a table. ``` ``` Which source supports this answer? ``` ### Permissions Workspace access is controlled by user roles and permissions. A user can only access the workspaces and data sources they have permission to use. For cloud integrations such as Microsoft 365, OneDrive, and SharePoint, Planck AI can also enforce source-level permissions so users only see documents they are allowed to access. ### Best practices Use separate workspaces when teams, permissions, or data sources need to be separated. Good workspace design helps keep answers more relevant and reduces the risk of exposing information to the wrong users. --- # 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: ``` GET https://planck-ai.gitbook.io/planck-ai-docs/documentation/getting-started-1/workspaces.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.