IDEAS home Printed from https://ideas.repec.org/a/das/njaigs/v1y2024i1p274-290id377.html
   My bibliography  Save this article

Autonomous GenAI Agents for Legacy-to-Cloud ETL Modernization

Author

Listed:
  • Vasudevan Ananthakrishnan
  • Shemeer Sulaiman Kunju
  • Radhakrishnan Pachyappan

Abstract

The modernization of Extract, Transform, Load (ETL) processes from legacy systems to cloud-native architectures is critical for enhancing scalability, agility, and cost-efficiency in enterprise data management. Traditional manual modernization approaches, however, are time-intensive, error-prone, and require specialized expertise. This research introduces a novel framework leveraging autonomous Generative AI (GenAI) agents to automate the end-to-end legacy-to-cloud ETL modernization. The proposed agents autonomously analyze legacy ETL logic (e.g., SQL scripts, COBOL jobs), redesign pipelines using cloud-native services (e.g., AWS Glue, Azure Data Factory), generate optimized transformation code, validate data integrity, and deploy modularized workflows. Evaluations across real-world financial and healthcare datasets demonstrate a 70% reduction in migration time, 40% lower operational costs, and 99.5% schema consistency compared to manual methods. The framework also enables continuous optimization via adaptive learning from runtime metrics. This work pioneers AI-driven automation for legacy system modernization, significantly accelerating cloud adoption while minimizing risks.

Suggested Citation

  • Vasudevan Ananthakrishnan & Shemeer Sulaiman Kunju & Radhakrishnan Pachyappan, 2024. "Autonomous GenAI Agents for Legacy-to-Cloud ETL Modernization," Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023, Open Knowledge, vol. 1(1), pages 274-290.
    • Handle: RePEc:das:njaigs:v:1:y:2024:i:1:p:274-290:id:377
    as

    Download full text from publisher

    File URL: https://newjaigs.com/index.php/JAIGS/article/view/377
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:das:njaigs:v:1:y:2024:i:1:p:274-290:id:377. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Open Knowledge (email available below). General contact details of provider: https://newjaigs.com/index.php/JAIGS/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.