From Paper to Structured JSON: An Agentic Workflow for Compliant BMR Digital Transformation

TL;DR

This paper introduces an AI-based workflow that efficiently converts complex, unstructured pharmaceutical batch records into structured JSON format, significantly reducing processing time and enabling large-scale digital transformation in compliance with GMP regulations.

Contribution

The paper presents a novel AI system that automates the conversion of unstructured BMRs into structured JSON with validation and compliance checks, improving speed and accuracy over manual methods.

Findings

Achieves high confidence scores (80-90%) in BMR conversion.

Reduces processing time from hours to minutes per record.

Supports scalable, human-in-the-loop digitization of pharmaceutical records.

Abstract

Pharmaceutical manufacturers generate thousands of batch manufacturing records (BMRs) each year under FDA 21 CFR Part 211 and EU GMP rules. These long documents combine tables, calculations, images, and handwritten notes, and are usually digitized by hand with hours of expert review per record. We present an AI workflow that converts unstructured BMRs into structured JSON using token based chunking, parallel large language model extraction, and a fixed schema that covers 11 content types while preserving the original Group-Phase-Step hierarchy. The system applies three layers of validation (JSON syntax, structural integrity of classes and references, and pharmaceutical compliance checks aligned with GMP) and reports coverage metrics for text, tables, images, and calculations. On three real BMRs between 15 and 66 pages, it achieves composite confidence scores in the low to high eighties while reducing processing time from hours to minutes on a single GPU. This enables practical, human in the loop BMR digitization at scale and unlocks historical manufacturing data for downstream analysis.