--- schema_version: "1" id: bde51bf99200c419d89b227b3ba0300735c1524ad345befac01054cdd334d78a title: Extracting Data from Digital and Scanned Documents collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/platform/264-0-0/automate_flow_concepts_document_processing.md canonical_url: https://help.salesforce.com/s/articleView?id=platform.automate_flow_concepts_document_processing.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: 980c54ea70fc3e7128e47fc6a13f318f8d69f5b68e337919b3da0e8ea75d6d3f description: Extract structured data from invoices, purchase orders, forms, and other unstructured or semi-structured documents using AI-powered analysis in Flow. Automate data entry and processing workflows by converting document content into structured information that can be used in your business processes. Use human review workflows to validate extracted data and ensure accuracy for critical business decisions. products: - Flow Builder - Salesforce Platform release: "264" --- # Extracting Data from Digital and Scanned Documents Extract structured data from invoices, purchase orders, forms, and other unstructured or semi-structured documents using AI-powered analysis in Flow. Automate data entry and processing workflows by converting document content into structured information that can be used in your business processes. Use human review workflows to validate extracted data and ensure accuracy for critical business decisions. ### Required Editions
Available in: Lightning Experience
View supported editions.
This feature requires the MuleSoft for Flow: IDP add-on. Professional Edition requires the API access add-on. To purchase, contact your Salesforce account executive.
Document processing features require Einstein generative AI turned on in Setup, and Data 360 provisioned and enabled for your org.
MuleSoft for Flow: IDP features used with Agentforce require the Foundations or Agentforce 1 edition. To purchase these editions, contact your Salesforce account executive.
## How Flow Extracts Data from Documents The document processing pipeline consists of these steps: - Configuration: Create document processing configurations in the Automation App to define the extraction rules and output structure for each type of document you want to process. These configurations specify which fields to extract, their data types, and optional instructions to help Einstein understand the document structure. - Processing: Use the Extract Data from Document action in your flows to submit documents for analysis. The action uses the specified document processing configuration to extract data and returns the results as structured information that you can use in subsequent flow elements. The action returns a dynamic Apex class containing all the extracted data, which you can then use in subsequent flow elements or send for human review. - Review: Require human review of extracted data directly in the Extract Data from Document action by configuring its Human Review Settings. The flow pauses, a reviewer validates or corrects the data in the Human Reviews tab of the Automation app, and the flow resumes. ## Document Processing Configurations A Document Processing Configuration defines the specific fields, tables, and columns to extract from documents. You can also provide human-language instructions to help Einstein better understand the document structure. For example, you can define fields such as Invoice Number and include instructions such as "Extract the invoice number from the field next to the vendor name in the document." ## Confidence Scores and Data Quality Einstein assigns confidence scores to indicate how certain it is about the accuracy of each extracted field. High confidence scores indicate reliable extraction; lower scores suggest manual review. To route only low-confidence extractions for review, set Human Review Settings on the Extract Data from Document action to Only when needed. In the review window, each field shows its confidence percentage. The action also returns a Needs Manual Review output, along with Correlation ID, Extracted Data, and Extracted Data (JSON), that you can use in later flow elements. ## When to Require Human Review Review workflows let you validate extracted data before your business processes use it. Use them when: - The confidence score for extracted data is low - Business rules require manual approval - You want to validate data accuracy before making decisions - Compliance requirements mandate human oversight To add human review, turn on Human Review Settings in the Extract Data from Document action. See [Extract Data from Document Action](https://help.salesforce.com/s/articleView?id=platform.automate_flow_ref_elements_actions_extract_data_from_document.htm&release=264.0.0&type=5 "Extract structured data from documents using AI-powered analysis, with optional human review before the flow continues."). ## How Human Review Settings Work In the Human Review Settings section of the Extract Data from Document action, choose when a review is required and who completes it. - **Never:** No review is created. The extracted data goes straight to the next element in the flow. - **Only when needed:** A review is created only when one or more extracted fields or table rows have a confidence score below the confidence threshold. If every value meets or exceeds the threshold, the flow continues without a review. - **Always:** A review is created for every document that the action processes, regardless of confidence scores. In Assigned To, you can select a user to own the review. If you leave Assigned To blank, the review is created without an assigned reviewer. When a review is created, the flow pauses at the action and holds all downstream elements until the review is submitted. Reviewers open the review from the All Human Reviews list in the Human Reviews tab of the Automation app. In the Document Review window, they compare the extracted data with the original document, edit values, and submit the review. See [Review Extracted Document Data](https://help.salesforce.com/s/articleView?id=platform.automate_flow_task_build_review_interface.htm&release=264.0.0&type=5 "Open a review that a flow created, compare the extracted data with the original document, correct any values, and submit the review so the flow resumes."). When the reviewer submits, the flow resumes and passes the reviewed values to the Completed path. If the review is rejected or times out, the flow doesn't continue on the Completed path. To run actions if no one completes the review in time, set the action's timeout (Amount of Time) and turn on Include timeout path. Otherwise, the flow fails with an error when the timeout expires. ## Supported Document Types This capability can process various types of business documents, including: - Invoices and receipts - Purchase orders and contracts - Forms and applications - Reports and statements - Scanned documents and images The AI models can extract text fields (names, addresses, descriptions), numeric values (amounts, quantities, percentages), dates and timestamps, and structured data (tables, forms) from both digital documents, scanned images, and handwritten text. ![Example](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-platform-platform_automation-264-0-0-production-enus/60568438-ec7e-4665-acd1-7c80dcbe60d5/images/icon_example.png) Example Here are specific examples of how organizations use document processing: - Invoice Processing: Extract invoice number, vendor name, amount, and due date from PDF invoices to automatically create or update invoice records in Salesforce. - Purchase Order Management: Process purchase orders to automatically update inventory systems and trigger reorder workflows when stock levels fall below thresholds. - Application Routing: Extract form data from loan applications or job applications to automatically route them to the appropriate teams based on content analysis. - Contract Compliance: Validate contract terms and automatically trigger approval workflows when specific clauses are detected. - Invoice Review: Set Human Review Settings to Only when needed so that a reviewer checks an invoice only when fields such as the bill-to state have low confidence scores. After the reviewer corrects the value and submits, the flow resumes and the Completed path creates an Account record from the corrected value. - **[Define What Data to Extract from Your Documents](https://help.salesforce.com/s/articleView?id=platform.automate_flow_task_define_data_extraction.htm&release=264.0.0&type=5)** Document Processing Configurations define the structure and rules for extracting data from your documents. By creating these configurations, you define what information to look for and how to organize the extracted data. This step is essential before you can process documents in your flows or set up review workflows. - **[Set Up Document Extraction and Routing to Human Review](https://help.salesforce.com/s/articleView?id=platform.automate_flow_task_setup_document_extraction_routing.htm&release=264.0.0&type=5)** Add the Extract Data from Document action to your flow, configure the document and configuration inputs, store the output, and route the extracted data to human review. - **[Review Extracted Document Data](https://help.salesforce.com/s/articleView?id=platform.automate_flow_task_build_review_interface.htm&release=264.0.0&type=5)** Open a review that a flow created, compare the extracted data with the original document, correct any values, and submit the review so the flow resumes. - **[Route Reviewed Data to Records and Business Processes](https://help.salesforce.com/s/articleView?id=platform.automate_flow_task_route_reviewed_data.htm&release=264.0.0&type=5)** Call the screen flow from the orchestration, branch on review outcomes, and add actions to update records, send notifications, or trigger other processes with the reviewed data. - **[Example Document Processing Workflows](https://help.salesforce.com/s/articleView?id=platform.automate_flow_concepts_example_document_processing_workflows.htm&release=264.0.0&type=5)** Walk through end-to-end examples that combine document extraction with human review, from a single flow path to record-triggered flows with approval and orchestration. - **[Document Processing Limits and Quotas](https://help.salesforce.com/s/articleView?id=platform.automate_flow_ref_idp_limits.htm&release=264.0.0&type=5)** Limits for document processing in flows align with Data 360 where applicable. Prompt limits and other document processing-specific quotas are documented in the MuleSoft document processing documentation.