> 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/core-concepts/documents.md). # Documents Documents are files that are uploaded or synced into Planck AI. Once a document is processed, users can ask questions about it through the AI assistant. Documents can be used on their own or together with other workspace data sources. ### Supported file types Planck AI can work with common business document formats, including: * PDF files * Excel files * CSV files * Text files Support may vary depending on your deployment and enabled integrations. ### How documents get into Planck AI Documents can be added in two main ways: #### Manual upload A user uploads a file directly into a workspace. This is useful for: * Reports * Spreadsheets * Contracts * Invoices * Project documents * Operational files #### Cloud sync An admin connects a cloud storage provider such as Microsoft 365, OneDrive, or SharePoint. Planck AI then syncs selected folders into a workspace. This is useful when documents already live in a company file system and should stay connected to their original access permissions. ### Processing status After a document is uploaded or synced, Planck AI processes it before it becomes available for search and question answering. Common states may include: * Uploaded * Processing * Processed * Failed If a document is still processing, it may not appear in answers yet. ### Asking questions about documents Users can ask questions such as: ``` Summarize this document. ``` ``` What are the key risks mentioned in this contract? ``` ``` Which invoices are above 10,000 euros? ``` ``` Find documents that mention delayed rollout milestones. ``` ``` Compare these two spreadsheets. ``` ### Answers and supporting context Planck AI may return: * Summaries * Tables * Extracted values * Comparisons * Source references * Follow-up suggestions For important decisions, users should review the supporting context and source material. ### Best practices Use clear file names so documents are easier to identify. Good examples: ``` Telco_Q1_2026_Invoice_Summary.xlsx ``` ``` Telecom_Network_KPI_Report_March_2026.pdf ``` Avoid vague names such as: ``` final.pdf ``` ``` new file.xlsx ``` Organized documents improve search quality and make it easier for users to understand the source of an answer. --- # 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/core-concepts/documents.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.