> For the complete documentation index, see [llms.txt](https://help.brieftech.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.brieftech.ai/reference/document-metadata-fields.md).
# Document metadata fields
BriefTech's AI pre-fills these fields for every document. You can override the editable fields (Date and Description) in the tab; corrections take effect immediately and flow through to your Document Index and court bundle.
| Field | Type | Description |
| -------------- | ------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Date | Date | The document's date. Used for sorting and for the date column in the Document Index. Documents with no date are treated as undated. |
| Description | Free text | A short description or summary of the document. Supports Markdown when formatted descriptions are enabled in the Document Index — except that a description beginning with a number and a full stop (for example `117.`) is shown as-is, rather than being turned into a numbered list. |
| Index Category | Free text | A category you set yourself to group documents in your index. Choose **Group by LOD category** while building an index to generate its headings from these values, and use a forward slash to nest them (for example `Pleadings/Statements of Case`). Unlike Document Class, which the AI assigns and you can't edit, Index Category is yours to fill in and change. |
| Document Class | AI-extracted (read-only) | The document's type or class, extracted automatically during processing. Not a Review column and not editable — see below. |
| # (Identifier) | Read-only | A per-document identifier shown in the on-screen file list (Files and Review tabs), for example BT-000001. BriefTech assigns it automatically; it cannot be edited and is not one of the columns in the exported Document Index. Show or hide it from the column picker like any other column — it appears in that list as the "#" column. |
## Editing fields
Three fields are editable inline in the tab. Double-click a Document Date or Document Description cell to open its editor; click a Labels cell to open the label picker. No other column in the tab can be edited.
* **Date** — double-click the cell to edit the date inline. This opens a free-text date editor, not a calendar; if the document has more than one detected date, a list of candidate dates appears for you to pick from.
* **Description** — double-click the cell to open an inline text editor; click outside to save. Hover the cell to reveal its action buttons:
* **Translate** — translates the description into another language. Available whether or not the field is locked.
* **Regenerate** — regenerates the AI description (see below). Shown only when the field is unlocked.
* **Use file name** — replaces the description with the document's file name (without its file extension). Shown only when the field is unlocked.
* **Lock / unlock** — locks the field (when unlocked) or unlocks it (when locked). It is greyed out while the description is empty — there is nothing to lock. When the field is locked, only this padlock and the translate button are shown.
* **Labels** — click the cell to open the label picker and apply a label to the document. Labels are applied by you, not the AI; see [Folders, labels, and collections](/reference/folders-labels-and-collections.md) for how they work.
* **Document Class** — this value is derived from the AI's primary and secondary classification. It is **not** a column in the Review tab and **cannot be edited**. To work with it, use the **Classes** group in the left-hand panel to filter documents by their class.
Cells show state as well as values:
* **Being analysed** — while BriefTech is still analysing a document, its Document Date and Document Description cells show a grey placeholder bar and cannot be edited; they become editable when analysis finishes.
* **No AI description** — a description the AI has not produced shows **Not found**.
* **No labels** — a document with no labels shows **None**.
* **Manual override** — a value held as a manual override is shown in a different colour from an AI value.
Changes save instantly — there is no Save button. A value you set by hand is marked as a manual override, and the AI will not overwrite it.
Pressing Enter in a cell locks it even if you changed nothing — the AI's own value is committed as your manual override. Clicking outside the cell without changing anything leaves it unlocked.
Clearing the field and saving does **not** bring the original AI value back — your current text is kept instead.
An unlocked Description cell shows the **Regenerate** button, which refills the field with a fresh AI description; a locked cell must first be unlocked with its padlock.
## Related
Folders, labels, and collections
How folders, labels, and collections organise documents in a matter.
---
# 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.brieftech.ai/reference/document-metadata-fields.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.