AI Extractions automatically extracts fields, tables, and footnotes at scale across a wide range of document layouts, and every extracted value is traceable back to its source document. Well-structured prompts in the description field are the key to accurate, consistent results. This article explains how to write them and how to refine them when a field is not extracting cleanly.

Use the description field to guide AI Extractions to the exact data you need. These principles help you get consistent results:

Scenario: extracting "401K" values from a document where the term appears multiple times in different contexts.

Key: "401K"

Instead of: an empty description, or just "401K value"

Use: "The version that is next to or under community depreciation"

Scenario: extracting footnotes from K1 tax forms that can appear in different formats.

Key: "Footnotes"

Instead of: "Get the footnotes"

Use: "Capture all elements that start with LINE, ITEM, or BOX. They can be in a table. They can be in two types [specify the types]. Ignore pages that just have listings and dumps of codes and how-to-use instructions."

Scenario: extracting province codes that should be two characters.

Key: "Province of employment"

Instead of: an empty description

Use: "Two character province code"

Scenario: extracting tax amounts from invoices where the tax may be labeled differently.

Key: "Tax amount"

Instead of: "Extract the tax amount"

Use: "Extract the tax amount (usually appears as a line item above the total, may be labeled as GST, VAT, Sales Tax, or Tax)"

Scenario: extracting dates from invoices where the date field may have different labels.

Key: "Invoice date"

Instead of: "Extract the date"

Use: "Extract the invoice date (may appear as 'Invoice Date', 'Date', 'Issued', or 'Bill Date', typically in MM/DD/YYYY or DD/MM/YYYY format)"

Scenario: extracting the final invoice total when multiple monetary amounts appear on the document.

Key: "Invoice total"

Instead of: "Extract the total"

Use: "Extract the invoice total (the final amount due after all taxes and discounts, not the subtotal or pre-tax amount). This is typically the largest number on the invoice and may be labeled 'Total', 'Amount Due', or 'Balance Due'"

The example below shows how a clear description field guides AI Extractions to the right values on a payroll report.

The schema description gives a concise overview of the extraction purpose and the type of content being processed. AI Extractions uses it during property extraction, so clear and precise descriptions improve accuracy.

Guidelines:

Results are extracted from the wrong location: add specific location descriptors to your field description. Example fix: "Extract 401K deduction (located under the accumulation date field, NOT the year-to-date 401K total shown in the summary section)."

Values are missing as non-duplicate entries: indicate in the prompt that all elements, including duplicates, should be extracted. Example fix: "Extract all names, including duplicates, under the personnel column."

Some values are missing: add a new key to target the missed elements, then merge keys and prompts. Example fix: "Extract all dates in YYYY/MM/DD with numerals. Extract all dates in Japanese."

Extraction is slow: extraction time depends on document complexity and may take 5 to 20 seconds per page, with a current limit of 300 pages per document. If it is too slow, run the template on a smaller set first, then split the set into smaller parts if needed.