Banking Done Right: Redefining Retail Banking with Language-Centric AI

2025-10-08

AI Summary

This work addresses two key challenges in digital banking: low operational efficiency of traditional multi-screen interfaces and the inability of conventional conversational AI systems to meet stringent regulatory compliance requirements. To this end, we propose Ryt AI—the first conversational banking agent framework globally approved by financial regulators. Methodologically, it employs a multi-LoRA collaborative agent architecture built upon ILMU, our proprietary closed-source large language model, integrating four core modules: risk control, intent recognition, payment processing, and question answering. It further incorporates deterministic safety guardrails, human-in-the-loop confirmation protocols, and a stateless audit architecture to ensure transaction security, verifiability, and full traceability. Our primary contribution is the first realization of natural-language-driven core financial transactions—not merely advisory interactions—thereby overcoming both technical and regulatory barriers to production-grade conversational banking. Deployment results demonstrate substantial improvements in user experience and operational efficiency, while maintaining low computational overhead and high auditability.

Technology Category

• Natural Language Processing: Safety and Robustness
• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. This represents the first global regulator-approved deployment worldwide where conversational AI functions as the primary banking interface, in contrast to prior assistants that have been limited to advisory or support roles. Built entirely in-house, Ryt AI is powered by ILMU, a closed-source LLM developed internally, and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). Each agent attaches a task-specific LoRA adapter to ILMU, which is hosted within the bank's infrastructure to ensure consistent behavior with minimal overhead. Deterministic guardrails, human-in-the-loop confirmation, and a stateless audit architecture provide defense-in-depth for security and compliance. The result is Banking Done Right: demonstrating that regulator-approved natural-language interfaces can reliably support core financial operations under strict governance.

Problem

• Enabling core banking transactions through natural language conversations
• Replacing rigid multi-screen workflows with LLM-powered dialogue agents
• Ensuring secure regulator-approved AI interfaces for financial operations

Innovation

• LLM-native agentic framework for banking transactions
• Closed-source LLM with task-specific LoRA adapters
• Deterministic guardrails and stateless audit architecture