> 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/guides/user-guide.md). # User Guide The User Guide explains how to use Planck AI in day-to-day work. Use this section if you want to ask questions, analyze documents, query connected data, continue conversations, and understand the outputs Planck AI generates. ### What you can do With Planck AI, users can: * Ask questions in natural language * Analyze documents, spreadsheets, and CSV files * Query connected databases * Search synced cloud files * Continue analysis through conversations * Generate summaries, tables, charts, and reports * Use workspace context and knowledge to improve answers * Create or run automation workflows where enabled ### Main user workflows #### Chat with documents Use document chat when you want to ask questions about PDFs, Excel files, CSV files, text files, or synced cloud documents. Examples: ``` Summarize this contract. ``` ``` Which invoices are above 10,000 euros? ``` ``` Find documents that mention delayed rollout milestones. ``` #### Chat with databases Use database chat when a workspace is connected to a database or business system. Examples: ``` Show monthly revenue for the last two quarters. ``` ``` Which suppliers had the highest spend this month? ``` ``` Break this down by region. ``` #### Continue a conversation Use follow-up questions when you want to refine an answer. Examples: ``` Show this as a table. ``` ``` Only include results from this month. ``` ``` Which source supports this answer? ``` ### Understanding outputs Depending on the question and data source, Planck AI may return: * Plain-language explanations * Tables * Charts * Maps * Extracted values * SQL or code snippets * Source references * Follow-up suggestions For business-critical decisions, always review the supporting context and source material. ### Good questions produce better answers Specific questions usually produce better results than vague questions. Good examples: ``` Show overdue invoices above 10,000 euros by customer. ``` ``` Summarize supplier spend for this month and group it by category. ``` ``` Compare planned rollout milestones with actual completion dates. ``` Less useful examples: ``` Analyze this. ``` ``` What is happening? ``` ``` Tell me everything. ``` ### Using workspace knowledge Planck AI can use workspace context and knowledge to improve answers. If enabled, users may be able to add or correct knowledge from chat. This helps Planck AI understand business-specific terminology, exceptions, policies, and rules. Examples: ``` Apex Holdings and Apex are the same customer. ``` ``` For German customers, use 30-day payment terms unless the contract says otherwise. ``` ``` When calculating supplier spend, exclude one-time setup fees. ``` ### Recommended next pages * **Chat with Documents** — learn how to ask questions about uploaded or synced files * **Chat with Databases** — learn how to query connected databases and business systems * **Workspace Context & Automations** — learn how Planck AI uses business context to support repeatable workflows --- # 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/guides/user-guide.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.