E-AGMatch: Schema Matching Approach Guided by an Agentic Prompt for ETL Automation

Abstract

Extract-Transform-Load (ETL) processes are essential for modern data-driven enterprises, enabling strategic business decision-making by integrating heterogeneous data sources into decision-support information systems. The reliability of ETL pipelines hinges on semantically correct schema matching between source schemas and the ETL-defined target schema. However, this task is complicated by schema heterogeneity and limited data access due to confidentiality constraints. Although many systems now leverage machine learning and large language models (LLMs), they still largely rely on manual intervention and large amounts of labeled data, resulting in low accuracy and limited adaptability to sensitive contexts. This paper proposes “E-AGMatch”, an automated hybrid schema matching approach powered by an open-source LLM. Its reasoning is guided by an agentic prompt built through advanced prompt engineering techniques and anchored with deterministic tools for scoring, voting, and verification. This design enables proactive schema correspondence generation while mitigating the typical LLM stochastic variability and ensuring result validation. A prototype evaluated on Purchase Order schema metadata showed promising performance, enhancing automation and reducing the requirement to access data.