Data Facts: A Metadata Schema for Structured Data Exchange in the NANDini Multi-Agent Ecosystem

2026-06-24

AI Summary

This work addresses the lack of structured data exchange mechanisms in existing agent communication protocols and the reliance on manual governance in enterprise data sharing, which hinder autonomous, real-time multi-agent interaction. To overcome these limitations, the paper introduces Data Facts—a lightweight JSON metadata schema that standardizes the description of dataset identity, access permissions, endpoints, validity periods, and integrity verification by embedding a data_facts_url pointer within Agent Facts. This approach enables, for the first time, fully autonomous data discovery, validation, and secure exchange without human intervention. Integrating SHA-256 checksums, TTL-based expiration control, and a three-layer security pipeline—comprising JWT authentication, capability-based gateway authorization, and agent-to-agent credential delegation—the system achieves 100% decision accuracy (versus 35.2% in the baseline), reduces stale-data errors to 8.8%, and ensures 100% tamper detection with zero data leakage.

Abstract

NANDini (Networked Agents Natural Distillation of Interconnected Nodal Intelligence) envisions an automated ecosystem where intelligent agents independently create, process, and exchange data to drive decisions at scale. Realizing this vision requires infrastructure beyond agent discovery and communication: agents must be able to advertise, evaluate, and verify the datasets they hold. Current protocols, including NANDA for federated registry and A2A and MCP for inter-agent messaging, address identity and communication but provide no mechanism for structured data exchange. Existing enterprise data-sharing frameworks, such as IDS-RAM, Gaia-X, and Ocean Protocol, assume human-in-the-loop governance that is incompatible with autonomous, real-time agent interactions. We introduce Data Facts, a core NANDini concept: a lightweight JSON metadata schema that bridges agent discovery and data access through a single pointer, `data_facts_url`, added to an existing Agent Facts registry record. The linked document encodes dataset identity, access tier, whether public, semi-private, or private, endpoint, a time-to-live for freshness validation, and a SHA-256 integrity checksum. For private and semi-private data, we implement a three-layer security pipeline: JWT authentication, capability-scoped gateway authorization, and an A2A credential delegation protocol. Across 840 decision-making evaluations, data-informed agents achieve 100% accuracy versus 35.2% without data access (p < 0.001); TTL enforcement reduces stale-data errors from 37.6% to 8.8%; checksum verification achieves 100% corruption detection at all injection rates; and the security pipeline blocks all 46 forgery attempts with zero data leakage.

Problem

• structured data exchange
• autonomous agents
• metadata schema
• data verification
• agent interoperability

Innovation

• Data Facts
• multi-agent ecosystem
• structured data exchange
• metadata schema
• autonomous data sharing