AI Generic Extraction

The AI Generic Extraction action reads a document with AI and pulls out whatever fields you describe — for any document type. It is the general-purpose sibling of AI Invoice Extraction: instead of a fixed invoice schema, this action has no built-in field set, so you tell it what to capture and it returns those values.

Use it whenever you want AI extraction on documents that are not invoices — applications, forms, statements, medical records, contracts, or any structured document — or when you simply want to describe the exact fields to capture rather than accept a fixed list.


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

How it differs from AI Invoice Extraction

Both actions read a document and store the extracted values on the Record, but they differ in one key way:

  • AI Invoice Extraction uses a fixed, built-in invoice schema (Vendor, Invoice Number, Invoice Date, line items, and so on). You do not describe the fields — they are always the same.
  • AI Generic Extraction has no fixed schema. You define every field to capture in Extra Instructions, and the action extracts exactly those. Turn on Include Other Data to also capture everything else the AI finds in the document.


Reach for Generic Extraction for any non-invoice document, and for invoices keep using AI Invoice Extraction so you get its tuned invoice schema for free.

The two-action pipeline

Extraction and indexing are two separate steps, joined by the data the first one writes:

  1. AI Generic Extraction reads the document and stores each value it finds on the Record as temporary data — header fields as Index_<name> and line-item fields as IndexLine_<name>, where <name> is the field name you gave it.
  2. The Generic Indexing action then maps those Index_* / IndexLine_* values into the real Record Type fields you choose.


Add AI Generic Extraction first, then Generic Indexing later in the same process.

Options

The action's settings are grouped into three tabs.

Document(s)

  • Active Document — When on, the action extracts from the active Record's document if one is available.
  • Found Documents — Extract only the first matching document, or all documents that match. When Active Document is on, this applies only when there is no active document.
  • Cat/Sub/Name — Restrict which documents are extracted by Category, SubCategory and Name. Leave blank to match any.


AI Level

  • Quality — Maps to an AI model:
    • Economy — low token cost; best for fewer, clean digital PDFs. (Economy does not support caching, so it is best for smaller volumes.)
    • Balanced — medium token cost; good for most document types.
    • Maximum Quality — high token cost; best for poor-quality scans, handwriting, or unusual layouts.


Advanced

  • Include Other Data — Off by default. Turn it on to capture every data element the AI finds, not just the fields you named — the "extract everything" mode. This can increase token counts sharply, so use it only when you need it and prefer documents of a few pages.
  • Extra Instructions — This is where you define what to extract. Name each field and say whether it is per-document (header) or per-line, for example "Capture the patient name as PatientName" or "Capture each line's part number as PartNumber (per line)". The names you use here become the AI Field Names you map in Generic Indexing.
  • Date Format — How ambiguous dates (for example 05/06/2025) are interpreted. System Default inherits the global Default Date Format from System Options; MDY or DMY forces the interpretation for this action.


TIPS

  1. Name your fields clearly and consistently in Extra Instructions — those exact names are what you type as the AI Field Name in the Generic Indexing action.
  2. Say whether each field is header or per-line. Per-line fields are stored as IndexLine_<name> and are mapped on the Line Item Fields tab of Generic Indexing.
  3. Use Include Other Data when you want a catch-all extraction and are not sure of every field name in advance — then map whichever fields you need afterward.
  4. Start with Balanced quality; move to Maximum Quality only if fields are being missed on poor scans, and try Economy for clean, low-volume digital PDFs.


NOTE ON (AI): Reading the document with 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.