IDP by Workato ​

Intelligent Document Processing (IDP) by Workato extracts data from images and PDFs and converts unstructured content into structured output. It returns the extracted data as datapills that you can map into ERP, CRM, and financial systems.

When to use IDP by Workato ​

Use IDP by Workato to process structured documents, such as invoices, receipts, and purchase orders, or define free-form schemas for unstructured and semi-structured documents, such as resumes. Common use cases include:

• Order to cash: Extract purchase order data so sales teams can map it to NetSuite without manual entry.
• Accounts payable: Automate invoice data extraction to reduce manual entry before sending the data to Coupa.
• Procure to pay: Extract data from invoices and delivery orders, cross-reference it against the system of record, and flag discrepancies for review.
• Expense management: Extract receipt and invoice data to simplify employee expense reporting and reimbursement.

How to use IDP by Workato ​

You can add IDP by Workato to a recipe like any other connector, and it doesn’t require you to set up a connection. This connector provides two actions:

• The Process document action extracts structured data from uploaded files and returns the results as datapills.
• The Classify document action analyzes document content and assigns the document to a predefined category with a confidence score.

Formats and limitations ​

IDP by Workato supports multiple document formats and languages:

• File types: IDP by Workato accepts files in PDF, PNG, JPG, WebP, and GIF formats. Documents must be clear and legible.
• Languages: IDP by Workato supports invoices and receipts in English, Chinese, Japanese, and Korean.

Consider the following limitations when you evaluate IDP by Workato for your use case:

• Document size limit: IDP by Workato processes PDFs up to 50 pages and recognizes up to 100 line items per document.
• JSON schema constraints: IDP by Workato supports up to 100 fields with a maximum of 5 nested levels. The total schema length must not exceed 15,000 characters.

Additionally, IDP by Workato has the following rate limits:

Confidence scores and validation ​

IDP by Workato assigns each extracted value a confidence score from 0 to 1. Higher scores indicate greater confidence that the value matches the expected data.

Confidence thresholds vary by use case. A threshold of around 0.95 is a common starting value. Review values with scores at or below 0.95 to catch unexpected results. Further testing with representative document types and languages may help you set a more reliable threshold. Small text, non-Latin characters, complex tables, and long line items can reduce extraction accuracy. Use legible documents and well-structured JSON schemas to improve extraction quality, and add validation checks to identify potential issues.

Feature availability ​

IDP by Workato is available for customers on specific pricing plans, in the US, EU, AU, JP, SG, IL, KR, and UK data centers. IDP by Workato models are hosted in the US, EU, and APAC data centers and respect data residency requirements where possible. IDP by Workato isn't available to workspaces in the CN data center. This reflects local regulatory requirements and Workato's commitment to data sovereignty and applies to our multi-tenant and Virtual Private Workato (VPW) offerings.

Enable IDP by Workato in your workspace ​

You must have the Environment admin role or the legacy Admin system role to enable IDP by Workato in your workspace.

Complete the following steps to enable IDP by Workato in your workspace: