The AI Document Split action examines scanned stacks of mixed documents — invoices, receipts, statements, purchase orders, correspondence, all fed through the scanner in a single pass — works out where each document starts and ends, and splits each stack into separate documents that stay in the same Record. It can split one stack, or every stack filed under the same Category, SubCategory and Name in a single run.


This makes it different from its two siblings. AI Invoice Split and AI Split and Index split a document into a new Record per document; this action keeps everything in the Record it started in. It is also different from AI Document Classification, which sorts pages into a Record Type's category tree — classification groups consecutive pages of the same kind together, so a run of ten invoices stays one document there. AI Document Split is for exactly that case: it separates documents even when neighboring documents are the same kind, and it needs no Record Type and no category tree at all.


Use it when a Record collects paperwork as one scan and you want each piece filed as its own named document — an employee file scanned in one pass, a loan record's supporting documents, a day's receipts scanned as a single batch.


AZURE ONLY: This is an AI action and runs only on Azure-hosted / AI-licensed sites.


How the split is found

The action watches what each page says about itself — what kind of document it is, who it is from, its document number, and its date. When a page clearly asserts a different identity than the page before it, a new document starts; pages that agree, or that say nothing, continue the current one. Nothing needs to be printed on the pages for this to work — no separator sheets, no barcodes, no page counts — and there is nothing you have to configure to make it split. When in doubt the AI keeps pages together rather than over-splitting.


The original stacked document is removed once the split completes, and the Record's other documents are not touched. If the AI decides the stack is really one document, it is simply renamed in place.


What the action captures

The AI has to read each document's header to find the boundaries, so the same call also captures each document's key values: the generated Name plus DocType, Vendor, DocNumber, Date, and Amount. The captures are held in memory for the rest of the workflow run as a JSON array — one object per new document, including the document's ID and page range, for every document split in the run — under a Temp Variable you can read back with [DMTEMP(SPLITDATA)]. Nothing is written to the Record unless Write to Line Items is on, in which case each new document also becomes one line item on the Record.


To use the values, follow this action with a JSON Loop over that variable. Inside the loop each captured value is available as OBJ:Name, OBJ:Vendor, OBJ:Amount and so on, and the actions you place there decide where the data goes — line items, an e-form table, Record fields, a REST call, or anywhere else. If the workflow does nothing with the variable, the values simply expire with the run; the split itself is already saved.


Documents whose boundaries the AI was unsure of get a Confidence of "low" and an AIWarning property in their JSON object, which the loop can filter on to route those for review.


Options

Document

Active Document — On to split the Record's active document when there is one. Otherwise the Cat/Sub/Name selector below chooses the source.


All Matching Documents — Off splits only the first document matching Cat/Sub/Name. On splits every matching document, one after another, in a single run. The list of documents is taken before anything is split, so the documents the split creates are not split again in the same run. If nothing matches, the action does nothing. When Active Document is on and there is an active document, only that document is split.


Name Documents — On (the default) gives each new document a descriptive name from what the AI sees on its pages. Off, the new documents keep the name of the document they were split from.


Cat/Sub/Name — Which documents on the Record to split. With All Matching Documents off and the selector blank, the Record's first document is split; with All Matching Documents on and the selector blank, every document on the Record is split.


Captured Data

Temp Variable Name — The name the captures JSON is stored under, SPLITDATA unless you change it. Leave the default so the JSON Loop that follows can always use [DMTEMP(SPLITDATA)]; change it only if one workflow runs two splits and needs to keep their results apart.


Extra Capture Fields — Optional. One line per field to capture beyond the standard set, or a constraint on how a standard field is read (allowed values, format, where it appears on the page). Each extra field appears as a property on that document's JSON object. Header values only — line items cannot be captured during a split.


Write to Line Items — On to add one line item to the Record for each new document, after the Record's last existing line. The line holds only the values you map in Line Item Fields below; the captures are still held in the Temp Variable as well. This option appears only on sites with an Enterprise license.


Line Item Fields — One row per value to write. Captured Value is the name of a captured value: Name, DocType, Vendor, DocNumber, Date, Amount, DocumentID, Pages, Category, SubCategory, Confidence, AIWarning, or one of your Extra Capture Fields by the name you gave it. Line Item Field Name is the line item field that receives it. Clean Up can tidy the value on the way in: Currency strips currency symbols and thousands separators, Date reformats the date.


AI Level

Quality — Balanced suits most business documents; Maximum costs more and is best for poor scans, dense pages, or subtle boundaries. Vision detection needs a capable model, so there is no Economy option for this action.


Advanced

Extra Instructions — Boundary rules specific to your documents, for example "Receipts are usually single pages" or "Terms and Conditions pages belong with the document before them". When in doubt the AI keeps pages together rather than over-splitting.



Processing several documents at once

When a Record collects more than one scanned stack — a new scan arriving each day, or a month of uploads filed under one Category — turn on All Matching Documents and set Cat/Sub/Name to select the stacks. One run splits them all, and the Temp Variable holds the captures for every new document, so a single JSON Loop placed after the action sees them all. With Write to Line Items on, each new document also gets its line item without any loop at all.


A common setup is an Add-In on the Record that users click at month end: everything scanned into the Record during the month is split, named, and added as line items in one step. An E-form with a Line Item Table then shows those lines.


Keep the documents the split creates out of the selector for later runs — for example by filing new scans under their own Name or SubCategory, or by moving the split documents with Change Document Properties. A document that is split a second time is simply renamed in place, but with Write to Line Items on it would get a second line item.


TIPS

  • If every document in the stack is the same kind and you want a new Record per document, use AI Split and Index (or AI Invoice Split for invoices) instead — those actions exist for that shape of work.
  • If you want the pages sorted into a Record Type's document categories rather than separated document by document, use AI Document Classification.
  • Put the JSON Loop immediately after this action in the same workflow. The captures in the Temp Variable live only for the workflow run, so a later, separate workflow cannot read them. To keep the values on the Record, turn on Write to Line Items or write them from the JSON Loop.
  • If the split is close but not right, describe the exception in Extra Instructions before reaching for Advanced quality — a sentence about continuation pages or single-page receipts usually fixes more than a bigger model does.



NOTE ON (AI): Detecting splits with vision AI consumes tokens and may incur extra fees. Workflow tokens are billed separately from End-User or Admin tokens — check with your sales rep for more information.