About Feature

Intelligent Document Processing (IDP) leverages advanced technologies such as Large Language Models(LLMs), machine learning (ML), and optical character recognition (OCR) to automatically extract critical information from documents. With IDP, organizations can automate manual document-based activities, reduce data entry errors and scale document processing to support digital transformation initiatives.

IDP supports data extraction from various document types. It allows users to extract top-level data and one related list table data, review extracted values and map them to target objects within Specright for reporting. 

Benefits:

1. Scalable - IDP can process multiple documents at a time and can scale as the request for data extraction increases.
2. Efficient and accurate - As data is automatically extracted using computer vision and machine learning there are less chances of manual user entry errors and it is faster than the manual data entry.
3. Intelligent - Rule based systems break whenever there is format change in the document template. IDP is an intelligent system which recognizes the document formats and extracts information without breaking.

Feature in a sentence

Automatically extract, review and map data to create specifications using AI-powered document processing in Specright.

What is Feature?

IDP automates data extraction from unstructured document formats (PDF, PNG, TIFF, JPEG). It uses OCR and LLMs or In-house ML Models to capture text and tables, then provides a review workflow for validation before submission into new records within target Specright objects.

• For end users: Simplifies record creation by auto-extracting fields and reducing manual data entry.
• For power users: Simplifies document review process by auto-extracting fields and reducing manual data entry.
• For administrators: Offers configurable mappings, permissions, and setup flexibility to meet organizational needs.
• For partners: Extends Specright’s value through automation and integration with compliance workflows.

Feature Video Link(s)

IDP (Intelligent Document Processing) Self Service using LLM Release 27: 

https://youtu.be/wDoEs9BBwAo?si=YZaknSSBXegW2tsF

IDP Self Service Enhancements- Summer 2025 Release 30:  

https://youtu.be/j-OwygFmFIs?si=45t9FRoWA_S75BP6

Release 31 - Enhancements: 

https://www.youtube.com/watch?v=OjYP-4yUFWE&t=1s

Release 33 - Enhancements: 

https://www.youtube.com/watch?v=Ppu62vDh0pg

Why did we build it?

Manual document processing is time-consuming and leaves room for error. Documents like COAs and COIs often arrive in inconsistent formats, making automation difficult. IDP was built to solve this challenge by applying Machine Learning, OCR and Large Language Models (LLMs), enabling faster, more accurate extraction of structured data for compliance, reporting and decision-making.

• For end users: Reduce repetitive manual data entry.
   
• For power users: Enable advanced reporting and analytics from digitized document data.
   
• For administrators: Provide scalable, configurable automation.
   
• For partners: Deliver a value-add capability in implementations for COAs, COIs or any other document types.

What customer problem does this solve?

Customers often struggle with inconsistent document formats and manual review processes that lead to inefficiency, data errors, and compliance risks. IDP solves this by:

• Automating extraction of critical fields from documents.
• Enabling configurable review workflows and mapping to business objects.
• Improving accuracy by utilizing top LLM providers, such as OpenAI and AWS Nova Models, or by employing customized, in-house ML models trained on a wide array of document templates.

Value Proposition / Marketing Copy

Intelligent Document Processing (IDP) uses AI to automatically extract structured data from unstructured documents—such as COAs, COIs, spec sheets, artwork, and compliance files—and map it directly into Specright. By eliminating manual data entry, IDP turns documents into searchable, report-ready product data. The system adapts to different document formats, ensuring reliable extraction even as templates change.

• Eliminate manual data entry at scale: Process high volumes of documents at once and reduce hours of manual work to minutes. Submit documents via email, supplier portal, or bulk upload.
• Improve accuracy and reliability: AI-driven extraction minimizes human error and avoids failures caused by changing document formats.
• Activate document data instantly: Review, validate, and map extracted fields—including tabular data—directly to Specright objects for reporting, compliance, and downstream workflows.

Where is IDP available?

Release Updates

Short Setup Summary

1. IDP Review Task.
2. Configure AWS Named Credentials for ML model access.
3. Grant Specright API permissions and assign profiles.
4. Clone and configure Document Analysis record page.

5. Configuring IDP Self Service (Recommended)

   a. How to add a new Document Type

   b. Review Screen for IDP Self Service

   c. Setting Up Email Alerts for Review Tasks 

   d. Setting Up Email Submission Option for Self Service Document types

   e. IDP Bulk Upload setup (optional)

   f. IDP Self Service Settings

   g. Setting Up IDP “Document Extraction” on Record Detail Page

6. Configuring IDP for In-house COA Processing via Specright Settings > IDP Configuration.

7. Configure IDP for In-house COI Processing via Specright Settings > IDP Configuration

   a. COI components.

   b. Steps to configure IDP for COI 

   c. Recommended Setup to gain value from COI automation.

8. Using IDP.