An Agentic Software Framework for Data Governance under DPDP

TL;DR

This paper introduces an agentic software framework that embeds compliance logic into autonomous agents to enhance data governance under India's DPDP law, ensuring transparency, adaptability, and scalability across various domains.

Contribution

It presents a novel agent-based framework integrating semantic understanding and data sensitivity reasoning for dynamic, transparent, and compliant data governance under legal regulations.

Findings

Effective in multiple domains including healthcare, education, and e-commerce.

Achieves scalable compliance through domain-specific anonymization strategies.

Demonstrates improved transparency and adaptability in data governance workflows.

Abstract

Despite the rise of data-driven software systems in the modern digital landscape, data governance under a legal framework remains a critical challenge. In India, the Digital Personal Data Protection (DPDP) Act mandates rigorous data privacy and compliance requirements, necessitating software frameworks that are both ethical and regulation-aware. From a software development perspective, traditional compliance tools often rely on hard-coded rules and static configurations, making them inflexible to dynamic policy updates or evolving legal contexts. Additionally, their monolithic architectures obscure decision-making processes, creating black-box behavior in critical governance workflows. Developing responsible AI software demands transparency, traceability, and adaptive enforcement mechanisms that make ethical decisions explainable. To address this challenge, a novel agentic framework is introduced to embed compliance logic directly into software agents that govern and adapt data policies. In this paper, the implementation focuses on the DPDP Act. The framework integrates KYU Agent and Compliance Agent for this purpose. KYU (Know-YourUser) Agent supports semantic understanding, user trustworthiness modelling and Compliance Agent uses data sensitivity reasoning within a goal-driven, agentic pipeline. The proposed framework, built using an open-sourced agentic framework and has been evaluated across ten diverse domains, including healthcare, education, and e-commerce. Its effectiveness under DPDP, measured via an Anonymization Score, demonstrates scalable, compliant data governance through masking, pseudonymization, and generalization strategies tailored to domain-specific needs. The proposed framework delivers scalable, transparent, and compliant data governance through collaborative agents, dynamic policy enforcement, and domain-aware anonymization.