> ## Documentation Index > Fetch the complete documentation index at: https://docs.insight.nobly.dk/llms.txt > Use this file to discover all available pages before exploring further. # Configuring the classification tree > Author the classification tree that drives AI document classification: branches, descriptions, extraction prompts, allowed keywords, page cap, and dataset-matching guidance. ## Where it lives The tree is edited under **Admin settings → AI → Document classification**. Viewing requires the *AI configuration view* permission; saving requires *AI configuration manage*. Everything document classification needs is configured on this one page: the tree itself, the main extraction prompt, the OCR page cap, and the dataset-matching guidance. ## Anatomy of the tree The tree's **root branches are everything the AI may classify an upload as** — a document matching none of them gets no suggestion. Each branch can hold sub-branches, splitting a broad category into progressively more specific ones. A branch with no children is a **leaf**, where keyword extraction runs. Each branch has: | Field | What it does | | ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Branch name** | The label shown at that classification step and in the walk shown to users. Must be unique among its siblings. | | **When to choose this branch** | Plain language describing what a document in this branch looks like. This is what the AI reads when deciding — quote exact phrases when near-identical branches must be told apart. | | **Document type** | Stamped on the path when the walk passes through this branch: it becomes the type suggestion. Exactly one branch on every root-to-leaf path must set it. | | **Shared extraction prompt** / **Keyword extraction** | Extraction instructions. On a branch with children they are *shared context*, passed down to every leaf below; on a leaf they guide the final extraction call itself. | | **Allowed keywords** | The keywords extraction may fill for documents passing through here. Empty inherits the level above — or all of the stamped type's keywords if no level restricts. Branches underneath can only narrow the set, never widen it. | **Split into sub-branches** turns a leaf into a decision step: extraction moves to the new leaves, which receive the branch's prompt on top of their own. Use it when one description can no longer handle a branch's variety. ## Writing good branch descriptions The *when to choose* text is the single biggest lever for classification quality: * **Use the document's own words.** The AI must quote evidence for every choice, so descriptions containing phrases that literally appear in those documents ("dividend statement", "lease agreement") give it something to anchor on. * **Say what a branch is *not* for.** When two branches attract the same documents, give the losing branch an explicit exclusion ("not for shareholder or dividend paperwork"). * **Keep siblings contrastive.** The AI only ever compares siblings at one level — write each description so it separates that branch from the others *at the same level*, not from the whole tree. If users report a document type landing in the wrong branch, check the walk in the confidence tooltip: it shows which step went wrong and what evidence was quoted. Sharpen the two competing descriptions rather than adding more branches. ## Prompts * **Main extraction prompt** — part of every extraction call, whichever branch a document takes. The classification steps never see it. Put universal rules here (formatting, "leave a keyword out when its value cannot be read", language conventions). * **Branch prompts** accumulate down the path: a leaf's extraction call receives the main prompt, every parent's shared prompt, then its own — in that order, in a single call with the document text. Write instructions once at the highest level they apply to instead of copying them into every leaf. ## Max pages **Max pages** caps how many pages are OCR'd per document; empty uses the default of 20. It is the one page cap for the whole analysis — classification and keyword extraction read the same text. Set it when your documents front-load their identity (letterhead, first-page summaries) and tail pages only add cost. ## Dataset-matching guidance When an extracted keyword value must map to an entry from a keyword dataset, the AI receives a shortlist of candidates together with the **matching guidance** configured on this page. Only the guidance section of that prompt is editable — the fixed part that makes the AI return a specific candidate cannot be changed. Leave it empty to use the built-in default. ## Validation Saving validates the tree and rejects, with a message naming the offending branch: * A blank branch name, or the reserved name "None of the above". * Duplicate names among root branches or among siblings. * A path stamping two document types, or a leaf whose path stamps none. * The same document type stamped on two different branches. * An allowed-keywords set that widens what a level above restricted. The same rules run in the editor before the request is sent, so most mistakes are caught as you type. ## Import and export **Export** downloads the tree as a JSON file; **Import** loads one into the editor for review — nothing is applied until you press **Save**. Use export/import to move a tree between environments or to keep versioned backups before larger restructurings.