1. Overview (Project Background)

This project was initiated to address the massive document creation burden and quality variance issues that arise in GC Biopharma's Annual Product Quality Review (APQR) process.
APQR is a critical quality task that requires regular preparation of reports spanning hundreds of pages based on data dispersed across multiple systems (LIMS, QMS, ERP, etc.), requiring significant time and resources for data collection, review, and organization.

Accordingly, GC Biopharma initiated the project with the goal of building a system that leverages AI technology to streamline the quality document creation process and ensure accuracy and consistency in document quality.

2. Challenge (Problem Definition)

Prior to project initiation, the quality document creation process had the following structural limitations.

• Massive document volume and repetitive work burden
  To create annual APQR reports spanning hundreds of pages, data had to be collected, processed, and reviewed from multiple systems, and the repetitive manual work created excessive workload.

• Human error and result variance
  Manual data entry and review processes had high error potential, and document quality and result consistency varied depending on individual staff capabilities.

• Data dispersion and utilization inefficiency
  Quality-related data was dispersed in silo form across multiple systems such as LIMS, QMS, and ERP, making integrated analysis and utilization difficult.

3. Solution (Resolution Approach)

GC Biopharma and MegazoneCloud built an AI-based quality document writing support system and implemented data integration, document automation, and accuracy enhancement in phases.

• Data platform construction
  We established a data platform capable of collecting, storing, processing, and analyzing quality-related data from QMS, LIMS, ERP, and other systems, providing a foundation for stable integrated management of data required for document creation.

• Prompt Engineering and Rule-based writing
  We applied prompt engineering for document summarization and key information extraction, and supplemented numerical calculations, format specification, and domain-specific logic with Rule-Based Coding to ensure accuracy and reliability of results.

• SQL-based Context Augmentation
  Through predefined SQL, we selectively retrieved necessary data and delivered the context to the LLM, minimizing hallucination and implementing responses based on internal data.

• Phased construction and enhancement approach
  We proceeded with the project in the form of PoC → Phase 1 construction → Phase 2 expansion, continuously improving prompts and features based on operational feedback.

4. Result (Achievements)

Through the construction of the AI-based quality document writing support system, we achieved the following tangible results.

• Significant reduction in document creation time
  We reduced the time spent on data collection, processing, analysis, and draft creation by over 2,845 hours, significantly alleviating staff workload.

• Ensured consistency and accuracy of document quality
  By generating documents based solely on system data, we reliably ensured consistent quality levels of deliverables and effectively prevented human error.

• Secured user satisfaction and expansion potential
  We received positive feedback from actual users regarding document standardization, reduced missing items, and improved data inquiry convenience, and secured expectations for expansion to additional quality documents.

• Implemented factory-specific customized report automation
  We established a system capable of automatically generating APQR and related reports for each of the Ochang, Eumseong, and Hwasun factories.