> For the complete documentation index, see [llms.txt](https://help.filed.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.filed.com/reference/products/ai-tax-prep/pre-entry-notes-tab.md). # Pre-entry notes tab Pre-Entry Notes is the AI's transparency layer. Before any data enters tax software, Filed surfaces everything it noticed during extraction: conflicts between documents, expected documents that were not uploaded, and documents it chose not to extract from. The goal is to let the preparer make informed decisions before the return is finalized. In the product these surface inside the Binder's Documents screen as two lists, Observations and Missing documents, alongside the binder's "Excluded / Not Taxable" category for documents the AI set aside. ## Observations Observations lists every issue the AI flagged during extraction and reconciliation. Each entry shows the affected form or field, the AI's explanation of what it found, and a severity level. Severities are Critical, High, Medium, and Low. See [Pre-Entry Notes Notifications](/reference/products/ai-tax-prep/pre-entry-notes-notifications.md) for what each severity means and how to respond. ## Missing documents The Missing documents view shows documents the AI expected to find but that were not uploaded. Filed identifies missing items by comparing uploaded content against the prior-year return: if a form appeared in the prior year but no equivalent was uploaded for the current year, Filed flags it here. Each entry shows what is missing and the AI's reason for expecting it. Each missing-document entry has an Upload action. If the document is genuinely not needed this year, for example a prior-year K-1 from a partnership the client no longer holds, the entry can be dismissed without uploading. The summary line at the top of the list reads: "Based on prior year return the client is missing documentation for X / Y items." The fraction shows how many items remain unresolved out of the total detected. Missing-document entries also appear as annotation flags on the source documents in the Binder, anchored to the location where the AI detected the gap. ## Excluded documents Documents the AI decided not to extract from are moved into the binder's "Excluded / Not Taxable" category, rather than a separate Pre-Entry Notes filter. The AI excludes a file when a more authoritative version exists (for example, an original W-2 when a corrected W-2C was also uploaded), when the document is a duplicate, or when it is not relevant to this return. If an exclusion was made in error, either by the AI automatically or by a preparer using the Exclude button on the Forms tab, the record is in that binder category. The form can be re-included by returning to the Forms tab. ## Reviewing Pre-Entry Notes before data entry The recommended sequence before triggering the data-entry bot: 1. Open Observations and review the Critical and High items first. These represent detected problems that are most likely to produce incorrect entries if left unaddressed. 2. Review the Medium and Low items and decide whether each is a real issue or a false positive. 3. Check Missing documents and upload anything material before entry runs. 4. Confirm the binder's "Excluded / Not Taxable" category is correct. ## How to respond to a specific note **Higher-severity issue (Critical or High).** Open the relevant document, compare the flagged values, determine which is correct (check source documents or consult the client), and correct the value in tax software during or after entry. **Lower-severity issue (Medium or Low).** Review the underlying document and decide whether the AI found a real problem or a false positive. If it is a false positive, proceed without action. **Missing document.** Upload the file via the Files panel on the client page or via "Upload files" on the Forms tab. If the document is intentionally absent this year, dismiss the entry. **Incorrectly excluded document.** Return to the Forms tab. Use View to inspect the document, then remove the exclusion. ## Binder cross-reference AI-flagged items are also surfaced in the Binder as colored annotation marks anchored to the exact location in the source document where the issue was detected. The Observations screen in the Binder shows a consolidated list of all flags and notes, each linked to its source page. --- # 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://help.filed.com/reference/products/ai-tax-prep/pre-entry-notes-tab.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.