> For the complete documentation index, see [llms.txt](https://docs.filed.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.filed.com/reference/products/binder/leadsheets.md). # Leadsheets ## What leadsheets are Leadsheets are the tax-review workpapers produced by Filed's AI Review product. They are the digital equivalent of traditional review leadsheets: structured workpapers that document what was reviewed and what conclusions were reached. Filed AI populates them automatically from the client's documents, and the review team works through them to complete the review engagement. Leadsheets appear in the Binder's Leads tab and are the primary workspace for the AI Review workflow. ## When the Leads tab appears The Leads tab is only visible when AI Review is enabled for this client. If the tab is not present in the Binder, AI Review has not been activated for this return. See the AI Review section for setup details. ## Row view - reviewing by leadsheet The default view in the Leads tab is the row view, which presents individual leadsheet rows in a spreadsheet-style grid. Each row corresponds to a specific item, figure, or assertion on the workpaper. From any row, the source document that supports that figure can be opened directly in the center viewer for verification. The Notes & flags feed in the right panel filters to show only activity relevant to the currently open leadsheet, so notes and flags placed during review are scoped to the sheet being worked. ## Issue view - reviewing by issue The issue view (accessed by switching to the issues sub-view) presents AI Review findings as cards grouped by the underlying issue they relate to rather than by sheet. This view is useful for scanning a specific type of problem across multiple sheets at once, where the row view is better suited for working through a single sheet methodically. ## Tracing a figure back to its source and prior year A leadsheet row is not just the current-year number - it carries the trail behind that number. Each row can show the prior-year value alongside the current figure, so a jump between years (a dividend total that doubled, a deduction that disappeared) is visible without opening the prior-year return separately. When a figure is an aggregation of several source amounts - for example, a dividends total built from several 1099-DIV forms - the row shows the components that were summed to reach it, not just the total. This makes it possible to check a rollup figure against its individual contributors instead of trusting the total on faith. From any row, the same reasoning connects to source: opening the source document from a row (see [Row view](#row-view---reviewing-by-leadsheet)) shows exactly which line on which document the AI used, at the level of an individual figure rather than the form as a whole. ## Deep-linking from AI Review AI Review can link directly into a specific leadsheet and a specific row in the Binder. Following such a link opens the Leads tab directly to the relevant sheet and highlights the relevant row. The row highlight clears when the user navigates away. This connection between AI Review issue cards and the underlying workpaper rows is how the review workflow surfaces detail-level evidence. ## Signing off on leadsheets Leadsheets support sign-off at two levels: an entire leadsheet can be signed off, or individual rows within a leadsheet can be signed off. Both use the same four-level sign-off model as document sign-off: Level 0 (AI implicit, applied automatically when there are no open AI issues), Level 1 (preparer), Level 2 (reviewer), and Level 3 (partner or admin). A leadsheet sign-off is a formal assertion that the workpaper has been reviewed at the signed level. Signing off at a higher level implies that lower-level review is complete. A sign-off on a leadsheet or row becomes stale if the leadsheet or row is modified after the sign-off was placed. The stale state is surfaced in the UI and the expected workflow is to address the change and sign off again. Sign-offs can be undone. See [Activity and Sign-off](/reference/products/binder/activity-and-sign-off.md) for the full sign-off model. ## Exporting leadsheets Leadsheets can be exported as Excel or CSV from the Binder download dialog. **Walkthrough: export leadsheets** 1. Open the Download dialog (Docs panel **⋯** menu → **Download workpaper**) and make sure **Leadsheets** is checked. Use the format selector next to it to choose between **Excel** and **CSV**. ![The Download dialog with the Leadsheets format selector showing Excel and CSV](https://storage.googleapis.com/filed-prod-public-assets/walkthroughs/leadsheet-export/image1.webp) 2. Click **Download** to generate the leadsheet export in the chosen format. --- # 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://docs.filed.com/reference/products/binder/leadsheets.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.